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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     비롯
    0.70
    ่ย
    0.67
    щё
    0.66
    략
    0.66
     oblivious
    0.65
     volut
    0.65
     primaries
    0.63
    覧
    0.63
    visional
    0.62
    etzten
    0.62
    POSITIVE LOGITS
     Wife
    0.79
    èle
    0.77
    疾患
    0.73
    ان
    0.72
    èles
    0.72
    Existe
    0.71
    ඵ
    0.71
    STORE
    0.71
    માં
    0.71
    Preis
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.