# `Tinkex.Regularizers.L1`
[🔗](https://github.com/North-Shore-AI/tinkex/blob/v0.4.0/lib/tinkex/regularizers/l1.ex#L1)

Adapter for L1 sparsity using NxPenalties primitives.

Supports selecting a target tensor from logprobs, probabilities,
or a field within `loss_fn_inputs`.

---

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