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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    பி
    1.03
    candy
    1.01
    ოში
    1.01
    🟠
    1.01
     kang
    0.98
    受到
    0.97
     productColor
    0.97
     如果
    0.96
    knopf
    0.96
    যদি
    0.95
    POSITIVE LOGITS
    ా
    0.97
     verder
    0.89
     Stück
    0.87
    所有人
    0.87
    ല്ലാം
    0.85
     weiterer
    0.84
    S
    0.83
     lahat
    0.83
    ünüz
    0.83
     подряд
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.