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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Resolved
    0.95
    ال
    0.93
    dt
    0.92
    السلام
    0.91
     বিস্তৃত
    0.91
     Disclaimer
    0.90
     পারে
    0.90
    不起
    0.90
    <0x80>
    0.90
    が集
    0.89
    POSITIVE LOGITS
     hubungan
    1.40
     rapporto
    1.36
     relacionamento
    1.30
    䥑
    1.29
     chamar
    1.28
     talento
    1.28
     pega
    1.27
    uart
    1.27
    Ө
    1.27
    verhalten
    1.26
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.