INDEX

Explanations

Star Trek episodes and characters

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

The neuron is highly sensitive to Star Trek–specific terms (ship names, characters, species, etc.).

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

references to the Star Trek franchise, including its characters, species, ships, and episode titles.

oai_token-act-pair · gpt-5

Triggered by @jyhe0408

references to Star Trek characters, episodes, and franchise-related content.

oai_token-act-pair · claude-4-5-sonnet

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 smokes

-0.79

 opto

-0.79

 savannah

-0.78

 nhận

-0.74

 брать

-0.73

uf

-0.71

ragalactic

-0.71

Zal

-0.70

⃘

-0.69

мей

-0.69

POSITIVE LOGITS

 Hiro

0.75

 белого

0.71

🧵

0.71

JK

0.70

 Valid

0.69

 Delta

0.68

 Voyager

0.68

}/*

0.68

zma

0.68

 Correct

0.67

Activations Density 0.019%

Star Trek episodes and characters

The neuron is highly sensitive to Star Trek–specific terms (ship names, characters, species, etc.).

references to the Star Trek franchise, including its characters, species, ships, and episode titles.

references to Star Trek characters, episodes, and franchise-related content.

No Known Activations

Star Trek episodes and characters

The neuron is highly sensitive to Star Trek–specific terms (ship names, characters, species, etc.).

references to the Star Trek franchise, including its characters, species, ships, and episode titles.

references to Star Trek characters, episodes, and franchise-related content.

No Known Activations