INDEX

Explanations

Nihon, Muñoz, Himachal, immuno

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

Japanese names or terms, particularly "Nihon" or related Japanese words and proper nouns.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

This neuron activates on tokens containing the root “nihil” (as in nihil, nihilistic, etc.).

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

-2.55

 גם

-2.33

</b>

-2.31

 může

-2.27

ка

-2.20

was

-2.16

皷

-2.11

isées

-2.09

😽

-2.08

 untill

-2.06

POSITIVE LOGITS

2.83

</h3>

2.66

 sebagai

2.52

”（

2.36

an

2.17

ୌ

2.16

）-

2.13

！！！！

2.11

.\\

2.09

Activations Density 0.027%

Nihon, Muñoz, Himachal, immuno

Japanese names or terms, particularly "Nihon" or related Japanese words and proper nouns.

This neuron activates on tokens containing the root “nihil” (as in nihil, nihilistic, etc.).

No Comments

No Known Activations

Nihon, Muñoz, Himachal, immuno

Japanese names or terms, particularly "Nihon" or related Japanese words and proper nouns.

This neuron activates on tokens containing the root “nihil” (as in nihil, nihilistic, etc.).

No Comments

No Known Activations