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

    Neuronpedia

    INDEX
    Explanations

    around followed by preposition/article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ல்
    1.58
    çe
    1.43
    𝖊
    1.43
    сей
    1.41
    をはじめ
    1.40
    𝖎
    1.39
    е
    1.37
    𝐞
    1.33
     முதல்
    1.32
    сі
    1.31
    POSITIVE LOGITS
    s
    2.42
    س
    1.69
    sdf
    1.67
    sides
    1.57
    tint
    1.52
     engender
    1.51
    g
    1.51
    tract
    1.48
    تج
    1.48
    ের
    1.48
    Act Density 0.013%

    No Known Activations