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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     мяг
    0.88
    já
    0.83
     mittens
    0.77
     energi
    0.76
     дли
    0.75
     эки
    0.75
     å
    0.75
     gripe
    0.74
     pendientes
    0.73
     длиной
    0.73
    POSITIVE LOGITS
    ATING
    0.76
    خص
    0.74
    ्म
    0.73
    ש
    0.70
     positively
    0.68
    𝑮
    0.68
    要知道
    0.67
    ifferentiating
    0.66
     វា
    0.64
    Ո
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.