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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     semua
    0.86
     jalan
    0.84
     COMPENSATION
    0.84
     AMAZING
    0.83
     recuperação
    0.82
     injective
    0.81
     outsource
    0.80
     lion
    0.80
     gonad
    0.79
     reducción
    0.78
    POSITIVE LOGITS
    )**
    0.79
    f
    0.78
    strup
    0.77
    **,
    0.75
    ae
    0.75
    †
    0.74
    **
    0.74
    hower
    0.72
    dde
    0.72
    Theo
    0.72
    Act Density 0.000%

    No Known Activations