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

    Neuronpedia

    INDEX
    Explanations

    humor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eneric
    -0.07
     joy
    -0.07
    frey
    -0.07
    ARSE
    -0.06
     rob
    -0.06
    ANY
    -0.06
    ERICA
    -0.06
    ardu
    -0.06
     Union
    -0.06
     potřeba
    -0.06
    POSITIVE LOGITS
    ाजन
    0.06
     lymph
    0.06
    070
    0.06
    _SOURCE
    0.06
    sage
    0.06
    ทำ
    0.06
    (links
    0.06
    _wait
    0.06
    .Ass
    0.06
     ripping
    0.06
    Act Density 0.045%

    No Known Activations