INDEX

Explanations

disease and health conditions

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

The neuron detects the word "illness" in medical or health-related contexts.

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

The neuron activates on occurrences of the word “illness” (i.e., it detects that exact medical term).

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

-2.84

最早

-2.52

鉕

-2.44

彞

-2.44

亊

-2.42

 έχουν

-2.41

т

-2.39

時間

-2.39

淶

-2.39

تیجه

-2.30

POSITIVE LOGITS

4.09

 Then

2.94

崀

2.47

⚣

2.44

⚋

2.33

He

2.28

骉

2.25

人也

2.20

 That

2.16

manian

2.13

Activations Density 0.004%

disease and health conditions

The neuron detects the word "illness" in medical or health-related contexts.

The neuron activates on occurrences of the word “illness” (i.e., it detects that exact medical term).

No Comments

No Known Activations

disease and health conditions

The neuron detects the word "illness" in medical or health-related contexts.

The neuron activates on occurrences of the word “illness” (i.e., it detects that exact medical term).

No Comments

No Known Activations