INDEX

Explanations

package/class names and specific terms

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

package and namespace declarations in Java code.

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

This neuron detects identifier tokens in Java package and import declarations (i.e. the individual package or module name segments).

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

 ſtre

-1.70

𐐀

-1.53

ATEGORY

-1.52

 rafraî

-1.48

 perpé

-1.48

筈

-1.46

of

-1.45

 noin

-1.45

 viſ

-1.43

 épu

-1.41

POSITIVE LOGITS

↵↵

1.93

↵↵↵

1.77

 with

1.74

and

1.63

en

1.49

</i>

1.49

so

1.48

 when

1.46

</u>

1.45

1.42

Activations Density 0.028%

package/class names and specific terms

package and namespace declarations in Java code.

This neuron detects identifier tokens in Java package and import declarations (i.e. the individual package or module name segments).

No Comments

No Known Activations

package/class names and specific terms

package and namespace declarations in Java code.

This neuron detects identifier tokens in Java package and import declarations (i.e. the individual package or module name segments).

No Comments

No Known Activations