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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kes
    -0.07
    ıldı
    -0.06
    mek
    -0.06
     kolo
    -0.06
    lek
    -0.06
    ivalence
    -0.06
     turn
    -0.06
    _first
    -0.06
    (bg
    -0.06
     rating
    -0.06
    POSITIVE LOGITS
     egregious
    0.07
    QDebug
    0.06
    .onerror
    0.06
     спас
    0.06
     candies
    0.06
    _updates
    0.06
     traditions
    0.06
    --,
    0.06
     jeux
    0.06
    dsa
    0.06
    Act Density 0.003%

    No Known Activations