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

    Neuronpedia

    INDEX
    Explanations

    code, algorithms, steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    em
    0.72
    es
    0.66
    are
    0.61
    o
    0.59
    ۲
    0.59
    as
    0.57
    om
    0.54
    te
    0.54
    ‍♀️
    0.52
    ိ
    0.52
    POSITIVE LOGITS
     алгорит
    0.72
     algoritmo
    0.68
     flowchart
    0.66
     чисел
    0.62
    代码
    0.61
     obsług
    0.60
     нейтро
    0.58
    اولة
    0.58
     участка
    0.57
     costruire
    0.57
    Act Density 1.185%

    No Known Activations