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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Farbe
    0.83
    㐄
    0.80
     stronę
    0.80
     Quiero
    0.79
     αυτά
    0.77
    ᒫ
    0.77
     which
    0.76
     Bedrooms
    0.76
     všetky
    0.76
     रहकर
    0.75
    POSITIVE LOGITS
    ak
    1.03
    на
    0.94
    ?"
    0.83
    не
    0.81
    ang
    0.75
    ad
    0.73
    un
    0.73
    rrbracket
    0.72
    ಾ
    0.71
    ?:
    0.71
    Act Density 0.773%

    No Known Activations