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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     selatan
    0.85
    asının
    0.80
     пье
    0.79
     blueberries
    0.77
     Minggu
    0.75
    ┈┈
    0.75
     rumores
    0.75
    <0x0C>
    0.73
    <0xCE>
    0.73
     panas
    0.73
    POSITIVE LOGITS
    نا
    0.78
    اً
    0.68
    з
    0.67
    غب
    0.66
    vaccinated
    0.66
    زن
    0.65
    可以
    0.64
    тим
    0.64
    าวิ
    0.63
    ناط
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.