INDEX

Explanations

from future import

np_acts-logits-general · gemini-2.5-flash-lite

This neuron is sensitive to the special double-underscore token (e.g. “”) used in Python’s “future__” and other dunder names.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</h1>

-2.05

</strong>

-1.70

-1.64

 luminosa

-1.63

 integran

-1.57

 decorativa

-1.52

<i>

-1.48

 ordinaria

-1.45

嘁

-1.44

 these

-1.42

POSITIVE LOGITS

ágeno

1.66

螣

1.62

 Roumanie

1.62

انتهای

1.59

ادامه

1.57

 takim

1.48

ୌ

1.46

,...

1.45

 бъдат

1.44

Gün

1.43

Activations Density 0.008%

from future import

This neuron is sensitive to the special double-underscore token (e.g. “”) used in Python’s “future__” and other dunder names.

No Comments

No Known Activations

from future import

This neuron is sensitive to the special double-underscore token (e.g. “”) used in Python’s “future__” and other dunder names.

No Comments

No Known Activations

from __future__ import

This neuron is sensitive to the special double-underscore token (e.g. “__”) used in Python’s “__future__” and other dunder names.

No Comments

No Known Activations

from __future__ import

This neuron is sensitive to the special double-underscore token (e.g. “__”) used in Python’s “__future__” and other dunder names.

No Comments

No Known Activations

from future import

This neuron is sensitive to the special double-underscore token (e.g. “”) used in Python’s “future__” and other dunder names.

from future import

This neuron is sensitive to the special double-underscore token (e.g. “”) used in Python’s “future__” and other dunder names.