# `Tinkex.Regularizers.Entropy`
[🔗](https://github.com/North-Shore-AI/tinkex/blob/v0.4.0/lib/tinkex/regularizers/entropy.ex#L1)

Entropy regularizer adapter using NxPenalties.

`:mode` controls whether entropy is encouraged (`:maximize`) or discouraged
(`:minimize`). The adapter maps these to NxPenalties' `:penalty`/`:bonus`
modes so the returned tensor can be used directly as a loss term.

---

*Consult [api-reference.md](api-reference.md) for complete listing*