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

    Neuronpedia

    INDEX
    Explanations

    odds and chances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .duration
    -0.08
     Committee
    -0.07
     Come
    -0.07
    (Category
    -0.07
    爱人
    -0.07
    度假
    -0.07
    Heavy
    -0.07
     bachelor
    -0.06
     saddle
    -0.06
    入学
    -0.06
    POSITIVE LOGITS
    엿
    0.07
    켯
    0.07
    ()][
    0.07
     exchanging
    0.07
    .tap
    0.07
     ef
    0.06
    𬘘
    0.06
    .REQUEST
    0.06
    ypical
    0.06
    _pushButton
    0.06
    Act Density 0.091%

    No Known Activations