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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    抵
    -0.07
    silent
    -0.07
    Signing
    -0.07
    返乡
    -0.07
    国内
    -0.07
     Mare
    -0.06
    .STATE
    -0.06
    مارك
    -0.06
     Px
    -0.06
    javax
    -0.06
    POSITIVE LOGITS
    חשבתי
    0.08
    按钮
    0.07
     balloons
    0.07
    _monitor
    0.07
    соедин
    0.07
    _row
    0.07
    があります
    0.07
    oro
    0.07
     Ces
    0.07
     cứng
    0.07
    Act Density 0.002%

    No Known Activations