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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enemies
    -0.08
    spi
    -0.07
    648
    -0.06
     Cardinal
    -0.06
     relaciones
    -0.06
    _poll
    -0.06
    568
    -0.06
    \htdocs
    -0.06
    typings
    -0.06
    ρη
    -0.06
    POSITIVE LOGITS
    еро
    0.07
    WARE
    0.07
    AST
    0.06
     Booking
    0.06
    (QWidget
    0.06
     prz
    0.06
     :↵
    0.06
    (find
    0.06
    "]),↵
    0.06
    áhnout
    0.06
    Act Density 0.024%

    No Known Activations