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

    Neuronpedia

    INDEX
    Explanations

    Let ... be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ்ட
    2.14
    %@",
    1.97
     mivel
    1.91
     prati
    1.89
    ভাবে
    1.82
     bonheur
    1.82
     preamble
    1.80
    *",
    1.78
     nhật
    1.78
     afl
    1.78
    POSITIVE LOGITS
    на
    2.60
    м
    2.11
    ن
    2.11
    О
    1.96
    お客様
    1.96
    DropDownStyle
    1.93
    or
    1.93
     dotycz
    1.92
     والمع
    1.91
    เป็น
    1.90
    Act Density 0.006%

    No Known Activations