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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _DIALOG
    -0.08
    �
    -0.07
     nord
    -0.07
     SIDE
    -0.07
    发改
    -0.07
    牌照
    -0.07
    .setX
    -0.07
    孵
    -0.06
    俙
    -0.06
    (NS
    -0.06
    POSITIVE LOGITS
     sys
    0.07
    實現
    0.07
     bleiben
    0.07
     ####
    0.07
    实现
    0.07
    -----
    0.06
     Dew
    0.06
    飞船
    0.06
    dismiss
    0.06
    _LINES
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.