INDEX

Explanations

structured data definitions

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

JSON or structured data formatting, particularly focusing on whitespace and opening braces/quotes.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron flags numeric measurement expressions—especially floating-point numbers and their associated units (e.g. “14.812 miles,” “23.25 miles,” “nm,” “knots,” or JSON-style decimals).

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

 then

-1.65

 between

-1.59

 about

-1.58

句話

-1.37

↵↵

-1.37

});

-1.33

 also

-1.33

 Tasche

-1.30

۔

-1.30

姉

-1.26

POSITIVE LOGITS

IZAR

1.46

Always

1.46

 всегда

1.43

依然

1.41

 πάντα

1.41

 هنوز

1.40

Still

1.39

1.38

Yet

1.37

눠

1.35

Activations Density 0.044%

structured data definitions

JSON or structured data formatting, particularly focusing on whitespace and opening braces/quotes.

The neuron flags numeric measurement expressions—especially floating-point numbers and their associated units (e.g. “14.812 miles,” “23.25 miles,” “nm,” “knots,” or JSON-style decimals).

No Comments

No Known Activations

structured data definitions

JSON or structured data formatting, particularly focusing on whitespace and opening braces/quotes.

The neuron flags numeric measurement expressions—especially floating-point numbers and their associated units (e.g. “14.812 miles,” “23.25 miles,” “nm,” “knots,” or JSON-style decimals).

No Comments

No Known Activations