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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ح
    0.49
    ي
    0.46
     restable
    0.44
    ش
    0.44
    ាក
    0.43
     ricev
    0.43
    AT
    0.43
    از
    0.43
    ER
    0.43
     Texans
    0.42
    POSITIVE LOGITS
    츤
    0.48
     소녀
    0.47
     문서
    0.46
    عنی
    0.46
     নির্দিষ্ট
    0.46
     tanggal
    0.45
     음식
    0.45
     වර්ග
    0.45
     kurzen
    0.45
     Интере
    0.45
    Act Density 0.008%

    No Known Activations