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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pdata
    -0.07
    )f
    -0.06
     oma
    -0.06
     Крім
    -0.06
     reservations
    -0.06
    [val
    -0.06
     Lav
    -0.06
     يو
    -0.06
     푸
    -0.06
     dye
    -0.06
    POSITIVE LOGITS
    	renderer
    0.07
    فر
    0.06
    .jpeg
    0.06
     rebut
    0.06
    agonal
    0.06
     상
    0.06
    underscore
    0.06
    реп
    0.06
    ////////////////////////////////////////////////////////////////////////
    0.06
    ปร
    0.06
    Act Density 0.005%

    No Known Activations