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

    Neuronpedia

    INDEX
    Explanations

    Operating systems and computers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lambda
    -0.07
    杜绝
    -0.07
     ((_
    -0.06
    博客
    -0.06
     puzzle
    -0.06
    uf
    -0.06
     certain
    -0.06
    #for
    -0.06
     variables
    -0.06
     presidents
    -0.06
    POSITIVE LOGITS
     slick
    0.07
     تماما
    0.07
    鄃
    0.07
    Anal
    0.07
    抃
    0.07
     AO
    0.07
    埤
    0.07
    แป
    0.06
     Magick
    0.06
     Opport
    0.06
    Act Density 0.066%

    No Known Activations