INDEX

Explanations

disease and health conditions

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

passages containing definitions or explanations of medical and health-related concepts.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

This neuron detects formal definitional or “defined‐as” statements—especially technical definitions often introduced by a date or number and keywords like “defined,” “is,” “state of,” “absence of,” etc.

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 салон

-0.88

 infanti

-0.83

お花

-0.80

 ändå

-0.79

Gui

-0.79

 Neuro

-0.77

Neuro

-0.76

 lycée

-0.76

 ISSUES

-0.75

POSITIVE LOGITS

 disease

1.94

 diseased

1.45

disease

1.42

 illness

1.37

 DISEASE

1.27

Disease

1.27

 Disease

1.23

 health

1.18

 malfunction

1.13

DISE

1.13

Activations Density 0.186%

disease and health conditions

passages containing definitions or explanations of medical and health-related concepts.

This neuron detects formal definitional or “defined‐as” statements—especially technical definitions often introduced by a date or number and keywords like “defined,” “is,” “state of,” “absence of,” etc.

No Known Activations

disease and health conditions

passages containing definitions or explanations of medical and health-related concepts.

This neuron detects formal definitional or “defined‐as” statements—especially technical definitions often introduced by a date or number and keywords like “defined,” “is,” “state of,” “absence of,” etc.

No Known Activations