INDEX

Explanations

lip and related medical/biological terms

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

variations of the word "Lip" at the beginning of names or scientific terms.

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

This neuron detects the three-letter sequence “lip” at the start of words or 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

-3.23

—

-2.98

–

-2.89

ありますが

-2.77

鸶

-2.53

-2.39

 come

-2.34

 have

-2.30

龊

-2.30

↵

-2.28

POSITIVE LOGITS

2.78

 When

2.72

 είναι

2.58

৹

2.48

Ꮨ

2.39

geſ

2.34

ised

2.31

меется

2.30

 необходимо

2.28

 perplexing

2.28

Activations Density 0.006%

lip and related medical/biological terms

variations of the word "Lip" at the beginning of names or scientific terms.

This neuron detects the three-letter sequence “lip” at the start of words or names.

No Comments

No Known Activations

lip and related medical/biological terms

variations of the word "Lip" at the beginning of names or scientific terms.

This neuron detects the three-letter sequence “lip” at the start of words or names.

No Comments

No Known Activations