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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    с
    0.68
    inerary
    0.59
    gcd
    0.59
    ️⃣
    0.58
     Normandy
    0.58
     Workout
    0.57
    ייש
    0.56
     Brownian
    0.55
     जानी
    0.55
    ับ
    0.55
    POSITIVE LOGITS
    ي
    0.93
     infants
    0.83
    ا
    0.73
    йки
    0.72
     czemu
    0.70
     vipp
    0.68
    احت
    0.67
    u
    0.66
     fxg
    0.66
     nourrice
    0.66
    Act Density 0.008%

    No Known Activations