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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chemas
    -0.07
    患
    -0.07
     site
    -0.07
     Пра
    -0.07
     учит
    -0.06
     nearby
    -0.06
    aine
    -0.06
    (dic
    -0.06
    _bn
    -0.06
    ’i
    -0.06
    POSITIVE LOGITS
    apur
    0.07
    _FILENO
    0.07
    еры
    0.06
    _inactive
    0.06
     TILE
    0.06
     alleviate
    0.06
    CREEN
    0.06
     ferment
    0.06
    ‌تواند
    0.06
    ем
    0.06
    Act Density 0.020%

    No Known Activations