Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    Detects self-referential first-person pronouns—places where the speaker refers to themselves.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     utmost
    -0.07
    “What
    -0.07
     spooky
    -0.06
    那
    -0.06
    ат
    -0.06
    (ExpectedConditions
    -0.06
    447
    -0.06
    前に
    -0.06
     attendee
    -0.06
     teamed
    -0.06
    POSITIVE LOGITS
     I
    0.10
    I
    0.10
    /i
    0.08
    …I
    0.08
    .I
    0.08
    	I
    0.07
    :I
    0.07
     i
    0.07
    -you
    0.07
    "I
    0.07
    Act Density 0.099%

    No Known Activations