\begin{equation} softmax\left(x_{i}\right) = \frac{\exp(x_{i})}{\sum_{j=1}^{n} \exp(x_{j})} \end{equation}
its “softmax”! max: amplifies the probability of the largest x_{i} soft: because it assign some probability to smaller x_{j} as well
its “softmax”! max: amplifies the probability of the largest x_{i} soft: because it assign some probability to smaller x_{j} as well