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

    Neuronpedia

    INDEX
    Explanations

    token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anh
    -0.08
     brings
    -0.07
    _^(
    -0.07
    .Magic
    -0.07
    Attachments
    -0.06
    upport
    -0.06
    乡村振兴
    -0.06
    elp
    -0.06
    驾
    -0.06
     Ban
    -0.06
    POSITIVE LOGITS
     חופ
    0.07
    そも
    0.07
    .tcp
    0.07
     بلد
    0.07
    每年都
    0.07
     идеальн
    0.07
     cały
    0.07
    elfast
    0.07
    过得
    0.07
    _coef
    0.07
    Act Density 0.002%

    No Known Activations