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

    Neuronpedia

    INDEX
    Explanations

    judge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sunday
    -0.07
    vat
    -0.07
    children
    -0.07
    _asset
    -0.07
    ्यव
    -0.06
     magical
    -0.06
    -system
    -0.06
     patrons
    -0.06
     kids
    -0.06
    保障
    -0.06
    POSITIVE LOGITS
    ись
    0.06
    <Course
    0.06
    ottenham
    0.06
    Translatef
    0.06
    ";↵↵↵
    0.06
    .
↵
    0.06
     ов
    0.06
    ';";↵
    0.06
    .",
    0.06
    ��索
    0.06
    Act Density 0.002%

    No Known Activations