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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    вной
    0.82
     поднима
    0.77
    ͆
    0.77
    ))$
    0.75
    iveness
    0.75
     головы
    0.73
    rowning
    0.70
     đỡ
    0.69
     vẻ
    0.68
     competitor
    0.67
    POSITIVE LOGITS
    ش
    0.99
    ان
    0.95
    ن
    0.93
    ل
    0.88
    AYA
    0.86
    ל
    0.86
    ר
    0.85
    بر
    0.79
    petite
    0.79
    たい
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.