INDEX

Explanations

obese, disease, fractures, arthritis, homophobic

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

medical condition suffixes like '-tic', '-ese', and '-ic' that describe health disorders or diseases.

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

This neuron detects specialized biomedical or clinical jargon—multi-syllabic, domain-specific terms common in scientific medical writing.

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

 quintessential

-2.03

怎样的

-1.94

 .......

-1.90

ية

-1.87

 thre

-1.83

seemed

-1.81

 wist

-1.80

ⵌ

-1.77

appeared

-1.77

 hefty

-1.75

POSITIVE LOGITS

2.05

 from

1.90

 makes

1.85

With

1.81

It

1.80

for

1.80

 ostensibly

1.80

 seems

1.77

 There

1.76

 supposedly

1.76

Activations Density 0.541%

obese, disease, fractures, arthritis, homophobic

medical condition suffixes like '-tic', '-ese', and '-ic' that describe health disorders or diseases.

This neuron detects specialized biomedical or clinical jargon—multi-syllabic, domain-specific terms common in scientific medical writing.

No Comments

No Known Activations

obese, disease, fractures, arthritis, homophobic

medical condition suffixes like '-tic', '-ese', and '-ic' that describe health disorders or diseases.

This neuron detects specialized biomedical or clinical jargon—multi-syllabic, domain-specific terms common in scientific medical writing.

No Comments

No Known Activations