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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    265
    -0.07
     Leo
    -0.06
    UIColor
    -0.06
     Proc
    -0.06
     SubLObject
    -0.06
    二
    -0.06
    ajax
    -0.06
    .look
    -0.06
    trust
    -0.06
    ibile
    -0.06
    POSITIVE LOGITS
     atte
    0.08
     trest
    0.07
     ousted
    0.07
     плани
    0.07
    ==-
    0.07
    ARGIN
    0.06
    第一次
    0.06
    =re
    0.06
     memorable
    0.06
     contre
    0.06
    Act Density 0.063%

    No Known Activations