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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    r
    1.02
    re
    0.99
    la
    0.93
    ll
    0.89
    ט
    0.82
     Of
    0.81
    g
    0.80
    x
    0.80
    nél
    0.80
    ra
    0.79
    POSITIVE LOGITS
     sickly
    0.88
     battered
    0.81
     документы
    0.80
     zahlreiche
    0.78
     seasonally
    0.78
     completos
    0.77
     acclaimed
    0.77
    рованный
    0.77
    сные
    0.76
     seasonal
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.