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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     jsou
    0.73
     are
    0.70
     είναι
    0.68
     आहे
    0.67
     são
    0.67
     არის
    0.66
     adalah
    0.64
     ہے
    0.60
    都是
    0.58
     have
    0.57
    POSITIVE LOGITS
     इसे
    0.73
     bunları
    0.61
    इसे
    0.60
     einen
    0.59
    스를
    0.59
    これを
    0.57
    金を
    0.57
     onları
    0.56
     इसको
    0.55
     તેને
    0.54
    Act Density 0.014%

    No Known Activations