INDEX

Explanations

mouth, oral, oropharynx

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

The neuron detects references to the mouth and oral cavity, including related anatomical terms like lips, jaws, and mouthpiece.

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

Triggered by @neilrathi

The neuron specifically responds to mentions of the mouth or closely related oral body parts (jaws, lips, teeth, esophagus).

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

—

-1.72

–

-1.56

”

-1.55

-1.54

アレル

-1.48

-1.43

’

-1.41

AN

-1.38

-1.37

POSITIVE LOGITS

 mouth

1.92

<bos>

1.82

</h2>

1.60

čiť

1.59

ﹶ

1.59

ATIVA

1.55

 Weltkrieg

1.47

 ..."

1.45

极其

1.45

铖

1.45

Activations Density 0.060%

mouth, oral, oropharynx

The neuron detects references to the mouth and oral cavity, including related anatomical terms like lips, jaws, and mouthpiece.

The neuron specifically responds to mentions of the mouth or closely related oral body parts (jaws, lips, teeth, esophagus).

No Known Activations

mouth, oral, oropharynx

The neuron detects references to the mouth and oral cavity, including related anatomical terms like lips, jaws, and mouthpiece.

The neuron specifically responds to mentions of the mouth or closely related oral body parts (jaws, lips, teeth, esophagus).

No Known Activations