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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simpl
    -0.07
    Paul
    -0.07
    /open
    -0.07
     bund
    -0.07
    淀粉
    -0.06
    סג
    -0.06
     pragmatic
    -0.06
     seas
    -0.06
     mm
    -0.06
    法学
    -0.06
    POSITIVE LOGITS
    솊
    0.07
     artículo
    0.07
    ateria
    0.07
     {});↵↵
    0.07
     basename
    0.07
    //----------------------------------------------------------------------------------------------------------------
    0.07
     candidacy
    0.07
    iosity
    0.07
    iance
    0.07
    (Post
    0.07
    Act Density 0.002%

    No Known Activations