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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assisted
    -0.07
     military
    -0.07
     rá
    -0.07
     pessoas
    -0.07
     {})
    -0.07
     sınır
    -0.07
    일
    -0.07
    🇲
    -0.07
     predictions
    -0.07
    "><?=$
    -0.07
    POSITIVE LOGITS
    rtype
    0.07
    gota
    0.07
     //!
    0.07
    东西
    0.07
     wiring
    0.07
    errat
    0.07
    ведение
    0.06
     middleware
    0.06
    Hi
    0.06
    etri
    0.06
    Act Density 0.002%

    No Known Activations