INDEX

Explanations

technical descriptions

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

technical or formal language describing processes, methods, or implementations, particularly in patent or technical documentation.

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

The neuron activates on tokens that express the act of using or employing something (e.g. “using,” “use,” “utilize,” “utilization,” and their equivalents).

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

if

-1.77

not

-1.58

 also

-1.45

裡的

-1.43

-1.41

 ",";

-1.38

(",");

-1.38

 wszyst

-1.37

 berupa

-1.37

 notable

-1.33

POSITIVE LOGITS

2.02

 flexibel

1.55

 finalement

1.52

 diable

1.49

 investir

1.48

but

1.48

dengan

1.47

 enjeux

1.47

哦

1.46

 réellement

1.45

Activations Density 0.025%

technical descriptions

technical or formal language describing processes, methods, or implementations, particularly in patent or technical documentation.

The neuron activates on tokens that express the act of using or employing something (e.g. “using,” “use,” “utilize,” “utilization,” and their equivalents).

No Comments

No Known Activations

technical descriptions

technical or formal language describing processes, methods, or implementations, particularly in patent or technical documentation.

The neuron activates on tokens that express the act of using or employing something (e.g. “using,” “use,” “utilize,” “utilization,” and their equivalents).

No Comments

No Known Activations