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

    Neuronpedia

    INDEX
    Explanations

    xy or Y

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fill
    -0.07
    稍稍
    -0.07
     Short
    -0.07
    <i
    -0.07
    <meta
    -0.07
     tender
    -0.07
    _preds
    -0.07
     Defaults
    -0.07
    <Client
    -0.07
    ✆
    -0.07
    POSITIVE LOGITS
    文娱
    0.07
     noted
    0.07
    羑
    0.07
     표
    0.07
    olkien
    0.07
     Winston
    0.07
    ARIABLE
    0.07
     participação
    0.07
     dịch
    0.07
     Đoàn
    0.06
    Act Density 0.007%

    No Known Activations