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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Teachers
    -0.07
    赇
    -0.07
    .uml
    -0.07
    财税
    -0.06
    瘋
    -0.06
    =plt
    -0.06
    教育
    -0.06
    =pk
    -0.06
    倬
    -0.06
    _Off
    -0.06
    POSITIVE LOGITS
    isoner
    0.07
     Prism
    0.07
     blocks
    0.07
    靰
    0.06
     simul
    0.06
    升降
    0.06
    ځ
    0.06
    /sc
    0.06
     משת
    0.06
    .Values
    0.06
    Act Density 0.001%

    No Known Activations