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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    색
    -0.08
    净水
    -0.08
     running
    -0.08
     gray
    -0.07
    _decrypt
    -0.07
     invit
    -0.07
     thiếu
    -0.07
     Serve
    -0.07
    夕
    -0.07
    -overlay
    -0.07
    POSITIVE LOGITS
    頂
    0.07
     imprint
    0.07
    筻
    0.07
    😸
    0.07
    奥巴
    0.07
    ,omitempty
    0.07
    .database
    0.06
    ヵ
    0.06
     있었다
    0.06
    合理
    0.06
    Act Density 0.001%

    No Known Activations