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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     абсолютно
    0.85
    )}')
    0.84
    звичай
    0.80
    ।--
    0.80
     particolarmente
    0.77
     argento
    0.77
     espl
    0.76
     médical
    0.76
     orgull
    0.76
    Ꮮ
    0.76
    POSITIVE LOGITS
     Serengeti
    0.72
     Osaka
    0.72
     crankshaft
    0.72
     Shandong
    0.69
     nắm
    0.68
     TypeScript
    0.67
    র্প
    0.66
    henko
    0.66
    ts
    0.66
     điểm
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.