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

    Neuronpedia

    INDEX
    Explanations

    Number sequences and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ortion
    -0.07
     probability
    -0.07
    -most
    -0.07
     supper
    -0.07
     Conservatives
    -0.06
    encer
    -0.06
     voters
    -0.06
    (title
    -0.06
     corporations
    -0.06
     decoder
    -0.06
    POSITIVE LOGITS
     jeux
    0.07
     Sakura
    0.07
     yAxis
    0.06
    裏
    0.06
     sass
    0.06
     ｀
    0.06
    _TRANSL
    0.06
    _push
    0.06
    -/
    0.06
     Pří
    0.06
    Act Density 0.049%

    No Known Activations