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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Media
    -0.07
    mmc
    -0.07
     strchr
    -0.06
    	Render
    -0.06
    !(↵
    -0.06
    _ACCESS
    -0.06
     Hu
    -0.06
    Andre
    -0.06
     Страна
    -0.06
     플레이
    -0.06
    POSITIVE LOGITS
    ille
    0.08
    lets
    0.07
     lighter
    0.07
     contrat
    0.07
    ял
    0.07
    л
    0.07
    lin
    0.07
    оп
    0.07
    چی
    0.07
    nek
    0.07
    Act Density 0.001%

    No Known Activations