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

    Neuronpedia

    INDEX
    Explanations

    prank

    np_max-act · gemini-2.0-flash

    tokens related to pranks, pranksters, and prank-calling (e.g., "prank", "pranknet", "pranksters").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    mentions of pranks, practical jokes, and mischievous trickery.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    thumbs
    -0.07
    _ke
    -0.06
     controvers
    -0.06
     Amph
    -0.06
    Dlg
    -0.06
    Notes
    -0.06
    TableModel
    -0.06
    Note
    -0.06
     Angelo
    -0.06
    phot
    -0.06
    POSITIVE LOGITS
    보았다
    0.06
    .<
    0.06
    locking
    0.06
     žádný
    0.06
    кт
    0.06
     проекту
    0.06
     plá
    0.06
    entionPolicy
    0.06
     omas
    0.06
    /operator
    0.06
    Act Density 0.049%

    No Known Activations