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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    тся
    0.84
    يز
    0.82
    ایی
    0.77
    ó
    0.75
    ौनक
    0.74
    วิ่ง
    0.73
    ็
    0.71
     deportivos
    0.70
    puede
    0.70
    ക്ക
    0.70
    POSITIVE LOGITS
    शील
    0.86
    from
    0.71
    uh
    0.68
    i
    0.68
    ST
    0.67
    uned
    0.67
    ge
    0.66
     smoothly
    0.65
    and
    0.64
                
    0.64
    Act Density 5.508%

    No Known Activations