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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verschiedenen
    -0.07
     Im
    -0.07
     […]↵
    -0.06
     Shib
    -0.06
    oland
    -0.06
    HP
    -0.06
     immature
    -0.06
    sell
    -0.06
    ným
    -0.06
    mailer
    -0.06
    POSITIVE LOGITS
    .di
    0.07
    0.06
    _fill
    0.06
    (proxy
    0.06
    。。
    0.06
     [\
    0.06
     scenic
    0.06
    ational
    0.06
     Vegetable
    0.06
    .setIcon
    0.06
    Act Density 0.014%

    No Known Activations