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

    Neuronpedia

    INDEX
    Explanations

    adjacent or neighboring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    1.85
     extinguisher
    1.51
     Arial
    1.48
    ँ
    1.46
    (!
    1.45
    ிய
    1.45
    นิยม
    1.37
     méridionale
    1.34
    тин
    1.30
    ক
    1.30
    POSITIVE LOGITS
    ok
    1.99
    して
    1.92
    ol
    1.89
    ﺭ
    1.88
    are
    1.86
    w
    1.75
    ens
    1.74
     وبين
    1.74
    of
    1.73
    ul
    1.73
    Act Density 0.075%

    No Known Activations