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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    t
    0.97
    ت
    0.89
    r
    0.88
    ut
    0.86
    in
    0.83
    machine
    0.80
    Machine
    0.79
    ق
    0.79
    Icon
    0.78
    س
    0.76
    POSITIVE LOGITS
     mieszkań
    0.82
     temperat
    0.80
     может
    0.77
    それを
    0.75
    न्दावन
    0.74
     pozwala
    0.72
     некоторых
    0.71
     آغاز
    0.70
     může
    0.70
     firmer
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.