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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +b
    -0.08
     fn
    -0.07
    ?>
↵
    -0.07
    ढ
    -0.07
    ("#{
    -0.07
     confession
    -0.07
    :')↵
    -0.07
    /colors
    -0.07
     worksheets
    -0.07
    hir
    -0.07
    POSITIVE LOGITS
    _SPI
    0.07
     Autos
    0.07
     OCT
    0.07
     Wolverine
    0.07
     Compatible
    0.07
    изатор
    0.07
     alte
    0.07
     sunglasses
    0.06
     Displays
    0.06
    兼具
    0.06
    Act Density 0.038%

    No Known Activations