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

    Neuronpedia

    INDEX
    Explanations

    section headings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vượt
    -0.08
    绝
    -0.08
    各异
    -0.07
    嶒
    -0.07
     слова
    -0.07
     swearing
    -0.07
    .strip
    -0.07
     השנה
    -0.07
     삭제
    -0.07
     зависимости
    -0.07
    POSITIVE LOGITS
    ömür
    0.07
    amm
    0.07
    Widgets
    0.06
    ：<
    0.06
    @g
    0.06
     ‫
    0.06
    dbContext
    0.06
    inance
    0.06
     memes
    0.06
     Eat
    0.06
    Act Density 0.000%

    No Known Activations