INDEX

Explanations

JWT security and scope

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

technical terms related to authentication, authorization, and security tokens (like JWT, OAuth, claims, and credentials).

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

The neuron fires most strongly on authentication- and token-related jargon—things like “jwt,” “alg,” “claims,” “provider,” 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

</h5>

-1.92

说不定

-1.78

 THERE

-1.47

it

-1.46

its

-1.43

Its

-1.36

of

-1.35

на

-1.34

 gobiernos

-1.31

 humanas

-1.31

POSITIVE LOGITS

</strong>

1.81

 fairly

1.30

 first

1.26

 fuertemente

1.25

 vuestra

1.24

赓

1.24

𖥦

1.23

 wildly

1.23

 strong

1.19

Using

1.19

Activations Density 0.023%

JWT security and scope

technical terms related to authentication, authorization, and security tokens (like JWT, OAuth, claims, and credentials).

The neuron fires most strongly on authentication- and token-related jargon—things like “jwt,” “alg,” “claims,” “provider,” etc.

No Comments

No Known Activations

JWT security and scope

technical terms related to authentication, authorization, and security tokens (like JWT, OAuth, claims, and credentials).

The neuron fires most strongly on authentication- and token-related jargon—things like “jwt,” “alg,” “claims,” “provider,” etc.

No Comments

No Known Activations