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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cabbage
    -0.08
    ISOString
    -0.07
    逑
    -0.07
    perm
    -0.07
    otropic
    -0.07
    WATCH
    -0.07
     elimin
    -0.07
    -invalid
    -0.07
    евич
    -0.07
    _scheme
    -0.07
    POSITIVE LOGITS
    كب
    0.07
    .Content
    0.07
    知名品牌
    0.07
     exhibited
    0.07
    캅
    0.07
    داد
    0.06
    ß
    0.06
    .pushButton
    0.06
     Defendant
    0.06
    …↵↵↵
    0.06
    Act Density 0.008%

    No Known Activations