logits
The vector of raw (non-normalized) predictions that a classification model generates, which is ordinarily then passed to a normalization function.
Plain English Explanation
The vector of raw (non-normalized) predictions that a classification model generates, which is ordinarily then passed to a normalization function. If the model is solving a multi-class classification problem, logits typically become an input to the softmax function. The softmax function then generates a vector of (normalized) probabilities with one value for each possible class.
How is it used?
Practitioners refer to logits when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.