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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ো
    1.96
    ים
    1.94
    ה
    1.93
    ો
    1.81
    k
    1.78
    بازی
    1.75
    హా
    1.69
    ل
    1.65
    ों
    1.65
    कर्ता
    1.62
    POSITIVE LOGITS
     bagi
    1.66
    ės
    1.60
    重要的是
    1.55
    这也是
    1.53
    께
    1.52
    SIMPLEX
    1.51
    InitStruct
    1.51
    $),
    1.49
     nto
    1.48
     fluids
    1.46
    Act Density 0.000%

    No Known Activations