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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chess
    -0.07
     삼
    -0.06
    ¿
    -0.06
     pand
    -0.06
    "value
    -0.06
    Vict
    -0.06
     DEALINGS
    -0.06
    Chess
    -0.06
     ===>
    -0.06
    ियत
    -0.06
    POSITIVE LOGITS
    md
    0.06
    ;i
    0.06
    antal
    0.06
    Link
    0.06
    ListComponent
    0.06
    тон
    0.06
    ňování
    0.06
    ,i
    0.06
    řev
    0.06
     дня
    0.06
    Act Density 0.036%

    No Known Activations