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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.82
     mercenaries
    0.80
     aktual
    0.78
     galleries
    0.77
    t
    0.77
    تس
    0.77
     knights
    0.75
     adherents
    0.74
    里面的
    0.73
     çift
    0.73
    POSITIVE LOGITS
    ная
    0.88
    ра
    0.74
    که
    0.70
     非常
    0.66
    са
    0.65
     Чтобы
    0.64
    на
    0.63
    ной
    0.63
    非常
    0.63
    ного
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.