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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    is
    1.09
    ায়
    1.01
    지
    1.01
    কে
    0.98
    ায়
    0.98
    د
    0.97
    ל
    0.93
    دين
    0.93
    inah
    0.93
    ai
    0.92
    POSITIVE LOGITS
    ور
    1.12
    ﻛ
    0.93
     médicas
    0.84
    к
    0.82
    РЕ
    0.79
    ਰ
    0.79
    pping
    0.76
    ra
    0.75
     अलावा
    0.75
    ෙන්ම
    0.75
    Act Density 0.000%

    No Known Activations