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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ل
    1.02
    ن
    0.97
    ت
    0.97
    l
    0.93
    م
    0.93
    د
    0.91
    ל
    0.90
    t
    0.86
    σ
    0.84
    র
    0.79
    POSITIVE LOGITS
     /$
    0.85
     NAB
    0.83
     giá
    0.80
     Número
    0.80
    ⏤
    0.80
     fountains
    0.80
     Kỳ
    0.79
     NPD
    0.79
    代引不可
    0.79
    }=$
    0.77
    Act Density 0.000%

    No Known Activations