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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     маршрут
    -0.07
    imon
    -0.07
    .SetInt
    -0.07
     country
    -0.07
     ragaz
    -0.06
     ברח
    -0.06
     astro
    -0.06
    '].'/
    -0.06
    深圳市
    -0.06
    怄
    -0.06
    POSITIVE LOGITS
     destructive
    0.07
    前述
    0.06
    Need
    0.06
    Recipe
    0.06
     вер
    0.06
     sto
    0.06
    semb
    0.06
    UTION
    0.06
     START
    0.06
     FormData
    0.06
    Act Density 0.111%

    No Known Activations