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

    Neuronpedia

    INDEX
    Explanations

    specifications/requirements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    His
    -0.07
    In
    -0.07
    _cor
    -0.06
    :convert
    -0.06
    comboBox
    -0.06
    032
    -0.06
     petroleum
    -0.06
     tac
    -0.06
    ongyang
    -0.06
    IN
    -0.06
    POSITIVE LOGITS
    สมาช
    0.06
     알고
    0.06
     Disposable
    0.06
    겠
    0.06
    Electric
    0.06
     관리자
    0.06
    <B
    0.06
    _DATABASE
    0.06
     causing
    0.06
    ."},↵
    0.06
    Act Density 0.098%

    No Known Activations