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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     welder
    0.98
     inhomogeneity
    0.86
    廖
    0.85
     Фо
    0.83
    枧
    0.81
     psychos
    0.79
     communaut
    0.79
    ﾎ
    0.78
     bolog
    0.78
    莒
    0.78
    POSITIVE LOGITS
     monarch
    2.07
     monarchs
    2.06
     KING
    2.00
    King
    1.98
     King
    1.98
     royal
    1.98
     king
    1.93
     Princess
    1.90
     Royal
    1.90
    royal
    1.89
    Act Density 2.306%

    No Known Activations