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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sneakers
    0.94
     Tierra
    0.92
     DMP
    0.92
     Uno
    0.89
     FIFA
    0.89
     DNS
    0.79
     WTO
    0.78
     EMA
    0.78
     OPS
    0.78
     $
    0.78
    POSITIVE LOGITS
     rusak
    1.07
    y
    1.02
     blaming
    1.02
     bounded
    1.01
    Clan
    0.99
    xception
    0.98
     antiga
    0.97
     keuntungan
    0.96
     kelamin
    0.96
    ContentLoaded
    0.95
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.