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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    á
    1.47
    í
    1.20
     niveles
    0.98
     는
    0.94
    ỷ
    0.92
     lleve
    0.91
    é
    0.91
     năng
    0.90
     варианты
    0.88
     movimentos
    0.88
    POSITIVE LOGITS
    ق
    1.30
    ע
    1.13
    在
    1.07
    কে
    1.04
    لي
    0.95
    ന്ന
    0.91
    gown
    0.91
    in
    0.90
    حافظ
    0.90
    ج
    0.90
    Act Density 0.000%

    No Known Activations