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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PF
    0.93
    arl
    0.91
    ल्या
    0.87
    ഞ്
    0.86
    ated
    0.83
    abody
    0.81
    Sean
    0.80
    漲
    0.78
    ાય
    0.78
    ඹ
    0.77
    POSITIVE LOGITS
    峩
    0.70
    {[
    0.69
    珴
    0.68
     emoc
    0.67
    이가
    0.66
    বার
    0.65
     fpr
    0.64
     оси
    0.64
    cima
    0.62
    뎅
    0.60
    Act Density 0.000%

    No Known Activations