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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hilton
    -0.07
    .Cookies
    -0.07
    이드
    -0.06
    .Large
    -0.06
    \Collections
    -0.06
    щий
    -0.06
    ---</
    -0.06
     استرات
    -0.06
    ivalence
    -0.06
     Adolf
    -0.06
    POSITIVE LOGITS
    ometry
    0.06
     outf
    0.06
    _r
    0.06
     아침
    0.06
     removable
    0.06
     toplum
    0.06
     laut
    0.06
    rof
    0.06
     lubric
    0.06
    ,))↵
    0.06
    Act Density 0.002%

    No Known Activations