INDEX

Explanations

LaTeX math and medical terms

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

LaTeX environment tags like itemize, equation, pmatrix, and matrix.

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

This neuron detects LaTeX environment closing commands (tokens appearing in “\end{…}” such as end{itemize}, end{equation}, or end{align}).

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

 only

-2.42

 this

-2.17

 after

-1.91

 before

-1.83

two

-1.82

 these

-1.78

it

-1.73

}>

-1.71

 stars

-1.70

 some

-1.66

POSITIVE LOGITS

ність

1.94

っているので

1.90

るので

1.84

粜

1.84

ats

1.81

zation

1.80

ala

1.79

ibly

1.79

ஂ

1.78

︲

1.78

Activations Density 0.000%

LaTeX math and medical terms

LaTeX environment tags like itemize, equation, pmatrix, and matrix.

This neuron detects LaTeX environment closing commands (tokens appearing in “\end{…}” such as end{itemize}, end{equation}, or end{align}).

No Comments

No Known Activations

LaTeX math and medical terms

LaTeX environment tags like itemize, equation, pmatrix, and matrix.

This neuron detects LaTeX environment closing commands (tokens appearing in “\end{…}” such as end{itemize}, end{equation}, or end{align}).

No Comments

No Known Activations