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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nn
    -0.07
    人群中
    -0.07
     EAR
    -0.07
     Math
    -0.07
    marvin
    -0.06
    帽子
    -0.06
    إبراه
    -0.06
    劓
    -0.06
    وعد
    -0.06
    春晚
    -0.06
    POSITIVE LOGITS
    unidad
    0.07
    .prompt
    0.07
    浰
    0.07
    .url
    0.07
    -mobile
    0.07
     Liberation
    0.07
    _Rel
    0.07
    statt
    0.06
     detached
    0.06
    튼
    0.06
    Act Density 0.006%

    No Known Activations