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

    Neuronpedia

    INDEX
    Explanations

    words ending in al or ial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    1.73
    ה
    1.48
    ק
    1.45
    ла
    1.36
    ด
    1.32
    さ
    1.31
    лари
    1.23
    kval
    1.21
    ή
    1.20
    上
    1.19
    POSITIVE LOGITS
    are
    1.13
    the
    1.10
    СТИ
    1.06
    阌
    1.02
    al
    1.02
    ر
    0.96
     август
    0.94
    to
    0.93
    Фото
    0.92
     brill
    0.91
    Act Density 0.522%

    No Known Activations