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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     compulsory
    -0.07
    (calc
    -0.07
    ሳ
    -0.07
    禁
    -0.07
     MARK
    -0.06
     CONF
    -0.06
    (ID
    -0.06
     thật
    -0.06
    部分地区
    -0.06
    _COL
    -0.06
    POSITIVE LOGITS
     QPainter
    0.07
     diret
    0.07
    聊聊
    0.07
    температур
    0.07
    ערכים
    0.07
    椸
    0.06
    主持召开
    0.06
     invokingState
    0.06
    קיים
    0.06
     교
    0.06
    Act Density 0.114%

    No Known Activations