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

    Neuronpedia

    INDEX
    Explanations

    numerical percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    尟
    0.46
    ):=
    0.43
    㽞
    0.41
    Pyrazole
    0.39
    䢎
    0.38
    㳻
    0.38
    :')
    0.38
    ;">
    0.37
     :");
    0.37
    ާއ
    0.37
    POSITIVE LOGITS
    %
    2.17
     percent
    2.14
    %,
    1.94
     %
    1.85
    %.
    1.85
    percent
    1.82
    %;
    1.77
    ％
    1.73
    %)
    1.71
     PERCENT
    1.69
    Act Density 0.056%

    No Known Activations