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

    Neuronpedia

    INDEX
    Explanations

    AP subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    2.38
    ا
    2.22
    től
    2.08
    ை
    1.98
    s
    1.97
     laparoscopic
    1.93
    ação
    1.88
     ढंग
    1.88
    <?
    1.76
    aient
    1.73
    POSITIVE LOGITS
    OR
    1.77
    ból
    1.77
    ic
    1.73
     تقریباً
    1.68
    ight
    1.65
    에는
    1.65
    of
    1.64
    ש
    1.63
    ores
    1.59
    ون
    1.59
    Act Density 0.013%

    No Known Activations