INDEX

Explanations

altering technical terms

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

technical or specialized terminology in formal or academic contexts, particularly in scientific, programming, or medical documentation.

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

This neuron detects technical or domain-specific noun phrases (e.g. “irradiation,” “return value,” “session variable,” “regex,” “mechanism,” etc.).

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

They

-1.47

Their

-1.45

ícia

-1.39

ınt

-1.38

 gastar

-1.26

MemoryWarning

-1.23

 résine

-1.22

znám

-1.21

 musia

-1.20

lepaskan

-1.20

POSITIVE LOGITS

by

2.03

to

1.84

the

1.66

its

1.57

 into

1.48

1.22

my

1.21

1.18

as

1.16

we

1.16

Activations Density 0.428%

altering technical terms

technical or specialized terminology in formal or academic contexts, particularly in scientific, programming, or medical documentation.

This neuron detects technical or domain-specific noun phrases (e.g. “irradiation,” “return value,” “session variable,” “regex,” “mechanism,” etc.).

No Comments

No Known Activations

altering technical terms

technical or specialized terminology in formal or academic contexts, particularly in scientific, programming, or medical documentation.

This neuron detects technical or domain-specific noun phrases (e.g. “irradiation,” “return value,” “session variable,” “regex,” “mechanism,” etc.).

No Comments

No Known Activations