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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ла
    1.11
    い
    0.94
    ための
    0.93
    ра
    0.89
     Trans
    0.85
     Beginning
    0.84
     Challenge
    0.84
    ב
    0.83
    то
    0.82
     Super
    0.82
    POSITIVE LOGITS
    zoeken
    1.02
     rumors
    0.97
    想着
    0.97
    surfing
    0.96
    searchText
    0.92
    timeInterval
    0.89
     いや
    0.88
    engo
    0.86
    liegt
    0.86
    由于
    0.86
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.