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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _mi
    -0.07
    TING
    -0.07
    螈
    -0.07
     Does
    -0.07
    _ATTRIBUTE
    -0.07
     squirrel
    -0.07
    五月
    -0.07
    坐下
    -0.06
    (a
    -0.06
    均价
    -0.06
    POSITIVE LOGITS
    軟體
    0.08
    Enjoy
    0.07
    生态文明
    0.07
    _real
    0.07
    .HE
    0.07
    (Position
    0.06
    Ắ
    0.06
     alum
    0.06
    常に
    0.06
    Par
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.