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

    Neuronpedia

    INDEX
    Explanations

    Maximizing value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     полностью
    -0.07
     vamos
    -0.07
     здоров
    -0.06
    吃
    -0.06
     você
    -0.06
    rtc
    -0.06
     continuing
    -0.06
    Bookmark
    -0.06
    side
    -0.06
     progressing
    -0.06
    POSITIVE LOGITS
    _ENUM
    0.07
    íš
    0.06
     tarif
    0.06
     Italy
    0.06
    ,it
    0.06
    (Output
    0.06
     yı
    0.06
    kům
    0.06
    เปล
    0.06
    कर
    0.06
    Act Density 0.032%

    No Known Activations