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

    Neuronpedia

    INDEX
    Explanations

    code/data manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )n
    -0.07
    *[
    -0.07
     handling
    -0.07
    ัด
    -0.07
     Ard
    -0.07
    calculate
    -0.06
     arrays
    -0.06
    imo
    -0.06
     dominated
    -0.06
     wxT
    -0.06
    POSITIVE LOGITS
     hè
    0.06
    $req
    0.06
     тысяч
    0.06
     нем
    0.06
    uppy
    0.06
    网站
    0.06
    اعدة
    0.06
     besteht
    0.06
    ิเวณ
    0.06
    ▋
    0.06
    Act Density 0.082%

    No Known Activations