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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ت
    1.02
    ن
    1.01
    ل
    0.96
    م
    0.95
    t
    0.89
    د
    0.87
    l
    0.86
    ट
    0.84
    σ
    0.84
    m
    0.80
    POSITIVE LOGITS
     NAB
    0.88
     Transplantation
    0.87
    代引不可
    0.85
     NPD
    0.85
     /$
    0.84
     Kỳ
    0.82
    }=$
    0.81
     sinful
    0.81
     Kins
    0.80
    ⏤
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.