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

    Neuronpedia

    INDEX
    Explanations

    structures, methods, implementations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pastor
    -0.07
    737
    -0.07
     cen
    -0.07
    обов
    -0.07
    ensively
    -0.06
    iks
    -0.06
    MODE
    -0.06
     Кол
    -0.06
    580
    -0.06
    162
    -0.06
    POSITIVE LOGITS
    &o
    0.07
     online
    0.07
    ，他
    0.06
    ‌پدی
    0.06
    _GUI
    0.06
    ologie
    0.06
     ""))↵
    0.06
    opo
    0.06
     Authority
    0.06
    できます
    0.06
    Act Density 0.101%

    No Known Activations