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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    最重要的
    -0.07
    в
    -0.07
     excited
    -0.06
    ��
    -0.06
     giấy
    -0.06
    有一位
    -0.06
    MenuStrip
    -0.06
     cl
    -0.06
    êm
    -0.06
    clusive
    -0.06
    POSITIVE LOGITS
    猹
    0.07
    _person
    0.07
    ：%
    0.07
     שצר
    0.07
    逝
    0.06
     watchers
    0.06
    的地步
    0.06
     Stretch
    0.06
     sane
    0.06
    按时
    0.06
    Act Density 0.029%

    No Known Activations