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

    Neuronpedia

    INDEX
    Explanations

    knowing in advance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dédi
    0.47
    мне
    0.47
    }}^{*}\
    0.47
     ativos
    0.46
    탰
    0.45
     jardín
    0.44
     ಮನೆ
    0.43
    રમાં
    0.43
     музе
    0.42
     ನನಗೆ
    0.42
    POSITIVE LOGITS
    ↵
    0.61
     the
    0.47
     unequivocally
    0.47
     The
    0.46
    '
    0.45
     an
    0.43
     conclusively
    0.43
     definitively
    0.42
     Lee
    0.41
     either
    0.39
    Act Density 0.002%

    No Known Activations