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

    Neuronpedia

    INDEX
    Explanations

    within a string, is like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibals
    0.40
     जाए
    0.37
     сем
    0.37
    年度
    0.36
     vuông
    0.36
     фотографи
    0.35
     শিষ
    0.35
    ayscale
    0.35
    álise
    0.35
    ⠛
    0.35
    POSITIVE LOGITS
     algorith
    0.42
     alphanumeric
    0.41
     Đầu
    0.40
    **,
    0.39
     inter
    0.38
     lopen
    0.37
    рья
    0.37
     projected
    0.37
     DeV
    0.37
     libertarian
    0.37
    Act Density 0.000%

    No Known Activations