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

    Neuronpedia

    INDEX
    Explanations

    fid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -linux
    -0.08
    XF
    -0.08
    enefit
    -0.07
    Orders
    -0.06
    egment
    -0.06
     Stereo
    -0.06
     dx
    -0.06
    其实
    -0.06
     Christoph
    -0.06
    /{
    -0.06
    POSITIVE LOGITS
    ifications
    0.07
    楽
    0.06
     フ
    0.06
     transformations
    0.06
     Мин
    0.06
    ρέπει
    0.06
    袋
    0.06
     дослідження
    0.06
     DONE
    0.06
     時
    0.06
    Act Density 0.338%

    No Known Activations