INDEX

Explanations

aws services

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

AWS SDK code and related AWS service references.

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

This neuron detects references to AWS libraries or services in import paths and URLs (e.g. “aws” in package or domain names).

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

our

-1.73

︲

-1.53

rdquo

-1.49

皤

-1.48

 unseres

-1.48

 those

-1.47

有很多

-1.47

,"

-1.44

 Grüße

-1.42

POSITIVE LOGITS

↵↵

2.09

of

1.43

 ingenuity

1.28

 точку

1.27

 palestra

1.23

 error

1.21

 distinto

1.20

鯷

1.19

 данным

1.19

felder

1.19

Activations Density 0.036%

aws services

AWS SDK code and related AWS service references.

This neuron detects references to AWS libraries or services in import paths and URLs (e.g. “aws” in package or domain names).

No Comments

No Known Activations

aws services

AWS SDK code and related AWS service references.

This neuron detects references to AWS libraries or services in import paths and URLs (e.g. “aws” in package or domain names).

No Comments

No Known Activations