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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marie
    -0.07
     bucket
    -0.06
    Clinton
    -0.06
    .RESET
    -0.06
    _GPIO
    -0.06
     Twig
    -0.06
     Boots
    -0.06
    /book
    -0.06
     ==========
    -0.06
     DPS
    -0.06
    POSITIVE LOGITS
    **,
    0.07
    аж
    0.07
    _ALLOW
    0.07
     будто
    0.06
    ();
↵
↵
↵
    0.06
    08
    0.06
     společně
    0.06
    樓
    0.06
     demonstrates
    0.06
     svým
    0.06
    Act Density 0.016%

    No Known Activations