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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    сти
    1.62
    वीं
    1.59
    mesa
    1.58
    主义
    1.57
    ʟ
    1.57
    ່
    1.53
     περίπτωση
    1.47
    いる
    1.45
    主義
    1.44
     largos
    1.43
    POSITIVE LOGITS
    م
    2.17
     ska
    1.92
    et
    1.92
    iin
    1.86
    lə
    1.86
    ﺍ
    1.82
    ości
    1.78
    onbury
    1.71
    ために
    1.70
    ための
    1.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.