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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ውነተኛ
    0.80
     personnages
    0.74
     YELLOW
    0.70
     borderColor
    0.70
     MASTER
    0.69
     NOMBRE
    0.68
    ائز
    0.67
     непотпуним
    0.65
     радика
    0.65
    ൾ
    0.65
    POSITIVE LOGITS
    s
    0.86
    tournament
    0.84
    m
    0.84
    t
    0.80
    p
    0.77
    le
    0.76
    ため
    0.75
    es
    0.74
    совой
    0.74
    detection
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.