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

    Neuronpedia

    INDEX
    Explanations

    Fern, buns, tab, uni, happ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    てください
    2.11
    venidos
    1.88
    tedir
    1.77
    𝑠
    1.69
    britannien
    1.67
    ので
    1.66
    てる
    1.64
    धिकारी
    1.63
    ﹚
    1.60
     ومع
    1.58
    POSITIVE LOGITS
    i
    3.22
    ه
    3.22
    a
    2.64
    n
    2.64
    ia
    2.53
    ে
    2.38
    ی
    2.28
    at
    2.27
    r
    2.25
    ി
    2.14
    Act Density 0.023%

    No Known Activations