INDEX

Explanations

medical disinfection and prostheses

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

names of technologies, products, or brands.

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

The neuron strongly activates on specialized or technical content words—often domain‐specific terms (e.g. “disinformation,” “disinfection,” “halogen,” “prostheses”)—independently of common function words.

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

</h6>

-3.27

嵛

-2.66

</td>

-2.64

”،

-2.61

?’

-2.59

 lousy

-2.59

齶

-2.55

句话

-2.48

 pricey

-2.48

 payé

-2.47

POSITIVE LOGITS

2.84

2.61

</strong>

2.61

蚡

2.39

cited

2.33

ープン

2.33

AÇÃO

2.31

鉏

2.27

2.23

ated

2.20

Activations Density 0.020%

medical disinfection and prostheses

names of technologies, products, or brands.

The neuron strongly activates on specialized or technical content words—often domain‐specific terms (e.g. “disinformation,” “disinfection,” “halogen,” “prostheses”)—independently of common function words.

No Comments

No Known Activations

medical disinfection and prostheses

names of technologies, products, or brands.

The neuron strongly activates on specialized or technical content words—often domain‐specific terms (e.g. “disinformation,” “disinfection,” “halogen,” “prostheses”)—independently of common function words.

No Comments

No Known Activations