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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bleue
    0.77
     flipping
    0.73
     leichter
    0.71
     फंडा
    0.68
     certaine
    0.66
     perils
    0.66
     خونه
    0.66
     klare
    0.66
     تغير
    0.65
    స్తూ
    0.64
    POSITIVE LOGITS
    (!
    0.80
    小説
    0.76
    owane
    0.75
    ermanfaat
    0.74
     موسیقی
    0.71
     നിരവധി
    0.71
    รถ
    0.70
     cibo
    0.70
    是一个
    0.69
    বাহিনী
    0.68
    Act Density 0.004%

    No Known Activations