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

    Neuronpedia

    INDEX
    Explanations

    char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    規劃
    -0.07
     Tou
    -0.07
    补偿
    -0.07
    []>
    -0.07
    力度
    -0.07
    SEE
    -0.07
    领导班子
    -0.07
     Initiative
    -0.07
    预算
    -0.06
    准入
    -0.06
    POSITIVE LOGITS
     และ
    0.08
     sickness
    0.07
     condemning
    0.07
     charge
    0.07
    descr
    0.07
    şa
    0.07
     shame
    0.07
     частности
    0.07
    _content
    0.07
    -and
    0.06
    Act Density 0.002%

    No Known Activations