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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Calcul
    -0.07
    -equ
    -0.07
     adapting
    -0.07
     zou
    -0.07
    .dp
    -0.07
    健康管理
    -0.07
    北斗
    -0.07
    _SCORE
    -0.07
    /high
    -0.07
     Magnus
    -0.06
    POSITIVE LOGITS
     onPressed
    0.07
     inflatable
    0.07
    铥
    0.07
    通话
    0.07
    经开
    0.07
    未经
    0.07
     홈
    0.06
    uras
    0.06
    ousedown
    0.06
    廣
    0.06
    Act Density 0.075%

    No Known Activations