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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ᱓
    0.39
     বিত
    0.38
    বিত
    0.38
     cakkh
    0.38
    atable
    0.36
     avanç
    0.36
    कार
    0.35
     complet
    0.35
    χή
    0.35
     thunderstorm
    0.35
    POSITIVE LOGITS
     powder
    0.40
     Bf
    0.40
    CTT
    0.40
    powder
    0.39
     Архивировано
    0.39
     पाउडर
    0.39
    ισε
    0.39
    Classe
    0.39
     联系
    0.38
    matmul
    0.38
    Act Density 0.001%

    No Known Activations