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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ка
    1.47
    un
    1.45
    Y
    1.35
    as
    1.34
    ˆ‚
    1.28
    ung
    1.25
    ko
    1.22
    у
    1.19
    tono
    1.18
    و
    1.16
    POSITIVE LOGITS
     means
    1.60
     sputum
    1.55
     cento
    1.50
    dır
    1.47
     produzir
    1.47
     daí
    1.47
     chamada
    1.46
     כך
    1.46
     malef
    1.45
     admis
    1.43
    Act Density 0.123%

    No Known Activations