INDEX

Explanations

java package names

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

package or namespace identifiers in code, particularly after the dot separator in multi-level hierarchical names.

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

This neuron detects sequences of dot-separated lowercase identifiers that form package or import paths in code.

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

on

-2.28

 with

-1.95

for

-1.94

 until

-1.93

by

-1.84

to

-1.63

 from

-1.61

gigabyte

-1.59

 during

-1.52

 since

-1.45

POSITIVE LOGITS

begin

1.51

":

1.43

 ceinture

1.42

',

1.41

 flotte

1.38

",

1.37

1.35

如

1.34

"'

1.34

 rédu

1.33

Activations Density 0.040%

java package names

package or namespace identifiers in code, particularly after the dot separator in multi-level hierarchical names.

This neuron detects sequences of dot-separated lowercase identifiers that form package or import paths in code.

No Comments

No Known Activations

java package names

package or namespace identifiers in code, particularly after the dot separator in multi-level hierarchical names.

This neuron detects sequences of dot-separated lowercase identifiers that form package or import paths in code.

No Comments

No Known Activations