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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ute
    1.57
    چھے
    1.44
    ান্তরিত
    1.43
    fr
    1.40
    грам
    1.39
    的這個
    1.36
    igny
    1.34
    क
    1.33
    padding
    1.33
    o
    1.31
    POSITIVE LOGITS
    𝖆
    1.89
    alities
    1.83
    ੀ
    1.79
     resolute
    1.77
    rg
    1.75
     integrand
    1.74
     zippers
    1.72
    र्दू
    1.71
     runways
    1.70
    $("
    1.67
    Act Density 0.000%

    No Known Activations