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

    Neuronpedia

    INDEX
    Explanations

    Rankings and popularity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     communism
    -0.07
     Respond
    -0.06
    ونا
    -0.06
     territory
    -0.06
    48
    -0.06
    /release
    -0.06
    fallback
    -0.06
    orida
    -0.06
     preferences
    -0.06
     schematic
    -0.06
    POSITIVE LOGITS
     Аль
    0.08
     massa
    0.07
    ับต
    0.07
     служби
    0.07
    cken
    0.07
     тка
    0.07
    PRESS
    0.06
     Чтобы
    0.06
    <n
    0.06
     suburb
    0.06
    Act Density 0.006%

    No Known Activations