INDEX

Explanations

languages and biological terms

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

references to biological tissues, organs, and bodily systems.

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

The neuron activates on common nouns in their plural form (i.e. words ending in “-s” that denote plural entities).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

њу

-1.16

heo

-1.15

ције

-1.12

 GETS

-1.11



-1.05

合わせた

-1.02

 vélos

-1.02

 ofere

-1.02

 Lipid

-1.01

 ストレッチ

-1.01

POSITIVE LOGITS

and

1.15

They

0.95

norsk

0.91

schöne

0.89

 german

0.88

丫头

0.85

ğ

0.85

 french

0.84

 aisladas

0.83

 विभिन्न

0.83

Activations Density 0.070%

languages and biological terms

references to biological tissues, organs, and bodily systems.

The neuron activates on common nouns in their plural form (i.e. words ending in “-s” that denote plural entities).

No Comments

No Known Activations

languages and biological terms

references to biological tissues, organs, and bodily systems.

The neuron activates on common nouns in their plural form (i.e. words ending in “-s” that denote plural entities).

No Comments

No Known Activations