INDEX

Explanations

Ed Sheeran, apolipoprotein E, originality

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

The neuron activates for acronyms, organization names, and proper nouns, particularly those with capitalized letters.

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

The neuron flags named entities and formal titles—proper nouns, acronyms, and similar specialized names.

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

注意事

-2.39

靫

-2.34



-2.30

趼

-2.30

 digno

-2.17

谖

-2.17

郵便局

-2.16

焢

-2.14

ματος

-2.11

 includ

-2.06

POSITIVE LOGITS

3.05

2.70

 sicheren

2.52

 vollen

2.48

 größten

2.47

頔

2.36

 mattino

2.36

 echten

2.33

2.30

 This

2.25

Activations Density 0.013%

Ed Sheeran, apolipoprotein E, originality

The neuron activates for acronyms, organization names, and proper nouns, particularly those with capitalized letters.

The neuron flags named entities and formal titles—proper nouns, acronyms, and similar specialized names.

No Comments

No Known Activations

Ed Sheeran, apolipoprotein E, originality

The neuron activates for acronyms, organization names, and proper nouns, particularly those with capitalized letters.

The neuron flags named entities and formal titles—proper nouns, acronyms, and similar specialized names.

No Comments

No Known Activations