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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     तौर
    0.68
    یه
    0.61
     имају
    0.59
     пожалуйста
    0.58
    ו
    0.58
     چنان
    0.58
    ர்
    0.57
    顗
    0.54
    ur
    0.54
    ний
    0.54
    POSITIVE LOGITS
     ultrasonic
    0.69
     doux
    0.59
    statt
    0.59
    ন
    0.58
     lång
    0.57
    ेच्छा
    0.56
     Ultrasonic
    0.56
     Bcl
    0.55
    ्य
    0.54
     पालन
    0.54
    Act Density 0.183%

    No Known Activations