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

    Neuronpedia

    INDEX
    Explanations

    community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     позволя
    -0.08
    _clause
    -0.07
     Gmail
    -0.07
    าตรฐาน
    -0.06
    스를
    -0.06
    енка
    -0.06
     найкра
    -0.06
    ْف
    -0.06
    _FIX
    -0.06
    έργ
    -0.06
    POSITIVE LOGITS
     Helena
    0.07
     LINE
    0.06
     Ell
    0.06
    istration
    0.06
    rese
    0.06
    .Override
    0.06
     Plex
    0.06
    Seleccion
    0.06
    IFICATION
    0.06
    (screen
    0.06
    Act Density 0.030%

    No Known Activations