INDEX

Explanations

application startup and rendering

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

method or function calls related to application initialization or main entry points.

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

The neuron detects calls to framework/library initialization or “mounting” APIs (e.g. ReactDOM.findDOMNode, bootstrap(), mount(), run()).

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

。

-1.64

 about

-1.52

）。

-1.51

!!!"

-1.45

of

-1.43

：“

-1.39

、

-1.37

嚳

-1.37

 שלך

-1.35

!"

-1.34

POSITIVE LOGITS

 volna

1.41

 tente

1.38

 зару

1.31

囮

1.23

 grosse

1.23

 senhora

1.23

ui

1.20

 haría

1.19

 philosophie

1.19

 scho

1.19

Activations Density 0.016%

application startup and rendering

method or function calls related to application initialization or main entry points.

The neuron detects calls to framework/library initialization or “mounting” APIs (e.g. ReactDOM.findDOMNode, bootstrap(), mount(), run()).

No Comments

No Known Activations

application startup and rendering

method or function calls related to application initialization or main entry points.

The neuron detects calls to framework/library initialization or “mounting” APIs (e.g. ReactDOM.findDOMNode, bootstrap(), mount(), run()).

No Comments

No Known Activations