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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ू
    0.81
    тари
    0.80
    ي
    0.79
    ल
    0.76
    лева
    0.75
     EDUCATION
    0.74
    та
    0.73
    ки
    0.73
    טת
    0.73
    на
    0.73
    POSITIVE LOGITS
     quente
    1.01
     peligro
    0.85
    ように
    0.83
     apaixon
    0.83
     excepcional
    0.82
     आरोपित
    0.82
    ような
    0.80
    োগ্য
    0.80
    detalle
    0.79
     desiderio
    0.79
    Act Density 0.000%

    No Known Activations