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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     EMC
    -0.07
    仃
    -0.07
    onces
    -0.07
     facilitated
    -0.07
    翛
    -0.07
    전자
    -0.07
    roat
    -0.07
    Ӭ
    -0.07
    揮
    -0.07
    _Move
    -0.07
    POSITIVE LOGITS
     stereotype
    0.07
    (poly
    0.07
     rejected
    0.07
    评论
    0.07
    理论
    0.06
     Corruption
    0.06
    _die
    0.06
    ptest
    0.06
     {
    0.06
    western
    0.06
    Act Density 0.011%

    No Known Activations