INDEX

Explanations

smoking cessation or risk factors

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

references to smoking as a health risk factor.

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

The neuron activates specifically on occurrences of the word “smoking.”

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

.”

-4.13

’

-3.34

-3.27

在他

-3.22

真的

-3.22

也是

-3.09

就

-3.06

-2.84

不是

-2.83

完全

-2.77

POSITIVE LOGITS

鬭

4.00

肜

2.88

𞤢

2.81

Ꮸ

2.70

辄

2.66

鷙

2.61

鋮

2.59

驀

2.59

鹪

2.59

2.53

Activations Density 0.014%

smoking cessation or risk factors

references to smoking as a health risk factor.

The neuron activates specifically on occurrences of the word “smoking.”

No Comments

No Known Activations

smoking cessation or risk factors

references to smoking as a health risk factor.

The neuron activates specifically on occurrences of the word “smoking.”

No Comments

No Known Activations