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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reception
    -0.08
    ائز
    -0.07
     Intermediate
    -0.06
    may
    -0.06
     Hell
    -0.06
     Msg
    -0.06
     pInfo
    -0.06
     Purch
    -0.06
     nonlinear
    -0.06
     Worksheets
    -0.06
    POSITIVE LOGITS
    보았다
    0.07
    asar
    0.06
    抜
    0.06
     astro
    0.06
    cit
    0.06
    sterreich
    0.06
     jika
    0.06
    をか
    0.06
     xem
    0.06
     ге
    0.06
    Act Density 0.034%

    No Known Activations