# What is Softmax? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Mathematical Foundations  
> **Canonical Citation:** [https://spidits.com/ai-glossary/softmax](https://spidits.com/ai-glossary/softmax)

## Definition
Softmax is an activation function that takes a vector of raw real numbers (logits) and normalizes them into a probability distribution where each value lies between 0 and 1, and all values sum to 1.

## Architectural Mechanics & Deep Dive
Softmax is a mathematical function that converts a vector of raw scores (logits) into a probability distribution that sums to 1. Typically applied at the final output layer of classification networks and self-attention models, softmax exponentiates each score and normalizes it, highlighting the dominant output class.

## Industry Applications & Real-World Use Cases
Multi-class classification output layers and scaling attention scores in the Transformer attention mechanism.

## Frequently Asked Questions

### Why is Softmax used in classification instead of simple normalization?
Softmax exponentiates the inputs, which exaggerates differences between values—making the largest value closer to 1 and smaller values closer to 0, providing a clear class prediction.

### How does temperature scaling affect the Softmax output?
A higher temperature flattens the distribution (increasing diversity/randomness), while a lower temperature makes the distribution sharper and more deterministic.

## Related Terminology
- [activation-function](https://spidits.com/ai-glossary/activation-function)
- [temperature](https://spidits.com/ai-glossary/temperature)
- [transformer](https://spidits.com/ai-glossary/transformer)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*