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

    Neuronpedia

    INDEX
    Explanations

    file formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guns
    -0.09
    ייק
    -0.09
     openings
    -0.08
     Humph
    -0.08
    арк
    -0.08
    ítő
    -0.08
     çeşitli
    -0.08
     WALL
    -0.08
    anii
    -0.08
    _statement
    -0.08
    POSITIVE LOGITS
    格式
    0.16
     format
    0.16
     формате
    0.14
     формат
    0.14
     formaat
    0.13
     conventions
    0.13
    Format
    0.13
     convention
    0.12
    Formato
    0.12
    FORMAT
    0.12
    Act Density 0.043%

    No Known Activations