thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Softmax

A function that converts a vector of raw scores (logits) into a probability distribution summing to 1.

Definition

Softmax exponentiates each logit and divides by the sum of exponentials. It is used in multiclass output layers, in attention to weight tokens, and in LLMs to turn logits into next-token probabilities, where temperature scales the logits before softmax.

Exam tip

Softmax outputs mutually exclusive class probabilities that sum to one.

Related terms