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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilevel
    -0.08
     indemn
    -0.07
    isir
    -0.07
    (si
    -0.07
     булды
    -0.07
    (parse
    -0.07
     зоны
    -0.07
     платы
    -0.07
     الزمن
    -0.07
     Engel
    -0.07
    POSITIVE LOGITS
     magnific
    0.08
    ообраз
    0.08
     最大
    0.08
     tremendously
    0.08
     Weihnachts
    0.08
     corn
    0.08
     verd
    0.08
     magnificent
    0.08
    اتر
    0.07
    瞬
    0.07
    Act Density 0.023%

    No Known Activations