INDEX

Explanations

regulatory compliance

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

This neuron strongly activates on the very first word of each new paragraph.

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

the word "these" when it refers back to previously mentioned accomplishments or goals.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

words featuring a voiced “z” sibilant sound, especially at the end of the word.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NOMBRE

0.84

 Tecnología

0.84

 Muitos

0.84

ಲೆಯ

0.81

 वसू

0.81

 veinte

0.80

 Alamos

0.79

 Европы

0.79

 szolgált

0.79

 京都

0.79

POSITIVE LOGITS

to

0.89

igt

0.87

ist

0.86

re

0.86

ar

0.85

for

0.83

о

0.82

0.79

ong

0.77

 conditions

0.77

Activations Density 0.000%

regulatory compliance

This neuron strongly activates on the very first word of each new paragraph.

the word "these" when it refers back to previously mentioned accomplishments or goals.

words featuring a voiced “z” sibilant sound, especially at the end of the word.

No Comments

No Known Activations