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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     diğer
    0.84
     több
    0.78
    lső
    0.76
    ட்கள்
    0.75
     biasa
    0.75
     retirer
    0.74
     evaporator
    0.73
    ネジ
    0.73
     personnes
    0.72
     allons
    0.71
    POSITIVE LOGITS
     바탕
    0.67
    ুদ্ধে
    0.66
     imaginable
    0.66
    جري
    0.65
     Conversations
    0.65
    HISTORY
    0.64
     нулю
    0.64
     концу
    0.64
     הב
    0.64
     tricked
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.