INDEX

Explanations

biological classification headings

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

section headings like "Species", "History", and "Personal life" in informational articles.

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

The neuron activates on section or subsection headings in the text (e.g. “Personal life,” “History,” “Species,” etc.).

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

 seleccionar

-1.21

 gebeten

-1.06

 ESPEC

-1.01

ayet

-1.00

MING

-0.97

 cargador

-0.96

 personnalisés

-0.93

 derniers

-0.93

 Strukt

-0.93

 verhind

-0.92

POSITIVE LOGITS

of

1.95

 this

1.89

 these

1.77

 here

1.53

any

1.41

for

1.34

 when

1.33

 because

1.31

 such

1.31

so

1.21

Activations Density 0.099%

biological classification headings

section headings like "Species", "History", and "Personal life" in informational articles.

The neuron activates on section or subsection headings in the text (e.g. “Personal life,” “History,” “Species,” etc.).

No Comments

No Known Activations

biological classification headings

section headings like "Species", "History", and "Personal life" in informational articles.

The neuron activates on section or subsection headings in the text (e.g. “Personal life,” “History,” “Species,” etc.).

No Comments

No Known Activations