INDEX

Explanations

object literals or definitions

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

opening curly braces that start object literals or code blocks in JavaScript/JSON.

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

The neuron activates on numeric literals—integers or decimals—wherever they appear in the text.

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

"<?

-1.36

 आगे

-1.35

 tandis

-1.34

 故事

-1.33

 самые

-1.31

we

-1.30

 eerste

-1.30

oría

-1.27

 πρώ

-1.27

 такие

-1.27

POSITIVE LOGITS

 that

1.73

 about

1.73

 something

1.41

 this

1.38

1.37

 regarding

1.27

华夏

1.25

นี้

1.18

 juiz

1.13

Activations Density 0.019%

object literals or definitions

opening curly braces that start object literals or code blocks in JavaScript/JSON.

The neuron activates on numeric literals—integers or decimals—wherever they appear in the text.

No Comments

No Known Activations

object literals or definitions

opening curly braces that start object literals or code blocks in JavaScript/JSON.

The neuron activates on numeric literals—integers or decimals—wherever they appear in the text.

No Comments

No Known Activations