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

    Neuronpedia

    INDEX
    Explanations

    Math functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tightening
    -0.08
     collaboratively
    -0.08
     solidarité
    -0.08
     administration
    -0.08
     tighten
    -0.08
     administered
    -0.07
     solidarity
    -0.07
     democrat
    -0.07
     Ís
    -0.07
    纪
    -0.07
    POSITIVE LOGITS
     asym
    0.09
     lim
    0.09
    lim
    0.09
    initis
    0.08
     periódico
    0.08
     towers
    0.08
     limp
    0.08
    /mod
    0.08
    (limit
    0.08
    override
    0.08
    Act Density 0.007%

    No Known Activations