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

    Neuronpedia

    INDEX
    Explanations

    code/equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billig
    -0.07
    animal
    -0.07
    -scrollbar
    -0.07
    чем
    -0.06
    渔
    -0.06
    جريدة
    -0.06
    \Route
    -0.06
    季度
    -0.06
    稆
    -0.06
    كيف
    -0.06
    POSITIVE LOGITS
     Fri
    0.07
     capac
    0.07
    Pos
    0.07
    lasses
    0.06
     Wrocław
    0.06
    Land
    0.06
     ctxt
    0.06
    	fd
    0.06
    .frames
    0.06
    Max
    0.06
    Act Density 0.077%

    No Known Activations