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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     وعلى
    0.72
    """
    0.70
     сад
    0.69
    悴
    0.66
     тик
    0.66
    гут
    0.65
     steered
    0.65
     simple
    0.64
     медицинской
    0.64
     във
    0.64
    POSITIVE LOGITS
    敌人
    0.90
    都没有
    0.78
    浥
    0.77
    ARE
    0.76
    neſs
    0.75
    传染
    0.75
    敵人
    0.75
    回报
    0.75
     dijadikan
    0.74
     Coroner
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.