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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deduct
    -0.07
    (.
    -0.07
    _Font
    -0.06
     ********
    -0.06
    rtc
    -0.06
    /module
    -0.06
    .ResponseBody
    -0.06
    /fw
    -0.06
    -Cs
    -0.06
    _vk
    -0.06
    POSITIVE LOGITS
     ROUND
    0.07
     Employ
    0.07
     QHBoxLayout
    0.06
     contenu
    0.06
     Liter
    0.06
     arriv
    0.06
     Salem
    0.06
    	priv
    0.06
    밍
    0.06
     edip
    0.06
    Act Density 0.012%

    No Known Activations