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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exodus
    0.54
     compute
    0.51
     تخلی
    0.49
     הפר
    0.48
    SF
    0.47
     opportunity
    0.47
    回收
    0.46
     pound
    0.46
     unpredict
    0.45
     fertile
    0.43
    POSITIVE LOGITS
     mé
    0.53
     доклад
    0.52
    ٨
    0.52
    ٧
    0.49
     جرم
    0.48
    ೭
    0.46
    ЕМ
    0.46
    ကျွန်
    0.46
    ————
    0.45
     свої
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.