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

    Neuronpedia

    INDEX
    Explanations

    code/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HY
    -0.07
     vystav
    -0.07
     qualifier
    -0.07
    /gpl
    -0.06
    véd
    -0.06
    (W
    -0.06
    过来
    -0.06
     wherein
    -0.06
    (SE
    -0.06
     аж
    -0.06
    POSITIVE LOGITS
     حل
    0.06
    271
    0.06
    esine
    0.06
    国际
    0.06
    cps
    0.06
     불
    0.06
     miracle
    0.06
     미국
    0.06
    �
    0.06
    0.06
    Act Density 0.010%

    No Known Activations