INDEX

Explanations

programming code, method calls

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

function or method calls in programming code, particularly those invoking system services or core functionality.

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

The neuron spikes on identifiers or commands that mix letters and digits or switch casing within a single token (e.g. CamelCase or letter-digit sequences).

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

 useAppContext

-2.19



-2.16

 TÉCN

-2.16

 dictates

-2.13

スポンサーリンク

-2.11

”?

-2.03

 venice

-2.03

⎆

-2.02

 一覧

-2.02

 Would

-2.00

POSITIVE LOGITS

2.22

2.00

 kleiner

1.94

1.93

&#

1.88

 города

1.86

ൎ

1.83

她的

1.79

Activations Density 0.001%

programming code, method calls

function or method calls in programming code, particularly those invoking system services or core functionality.

The neuron spikes on identifiers or commands that mix letters and digits or switch casing within a single token (e.g. CamelCase or letter-digit sequences).

No Comments

No Known Activations

programming code, method calls

function or method calls in programming code, particularly those invoking system services or core functionality.

The neuron spikes on identifiers or commands that mix letters and digits or switch casing within a single token (e.g. CamelCase or letter-digit sequences).

No Comments

No Known Activations