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

    Neuronpedia

    INDEX
    Explanations

    racing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     averaging
    -0.08
    wach
    -0.07
     petro
    -0.07
     Aver
    -0.07
    umen
    -0.07
    chim
    -0.07
     eficiente
    -0.07
     lín
    -0.07
     rumah
    -0.07
     ನಿರ್ದೇಶ
    -0.07
    POSITIVE LOGITS
     thrill
    0.10
    ，因为
    0.09
     flutter
    0.09
    骤
    0.09
     순간
    0.09
     exhilar
    0.09
     excitement
    0.09
    milliseconds
    0.09
     الأحداث
    0.08
     aktiviert
    0.08
    Act Density 0.015%

    No Known Activations