INDEX

Explanations

googling for information

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

text describing online searches or requests for information, particularly phrases indicating unsuccessful searches or lack of results.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron fires on words and phrases related to performing or describing an online search (e.g. “Google,” “how,” “pictures,” and quoted query terms).

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

Năm

-1.26

↵↵

-1.21

大

-1.16

 dedicado

-1.13

Một

-1.12

 chico

-1.11

我们

-1.10

 jouet

-1.10

日

-1.09

总

-1.09

POSITIVE LOGITS

to

1.68

 eğer

1.22

it

1.20

 가능

1.20

하며

1.18

诃

1.17

 about

1.16

 possible

1.14

ullaby

1.13

edah

1.13

Activations Density 0.178%

googling for information

text describing online searches or requests for information, particularly phrases indicating unsuccessful searches or lack of results.

The neuron fires on words and phrases related to performing or describing an online search (e.g. “Google,” “how,” “pictures,” and quoted query terms).

No Comments

No Known Activations

googling for information

text describing online searches or requests for information, particularly phrases indicating unsuccessful searches or lack of results.

The neuron fires on words and phrases related to performing or describing an online search (e.g. “Google,” “how,” “pictures,” and quoted query terms).

No Comments

No Known Activations