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

    Neuronpedia

    INDEX
    Explanations

    Cosmos/universe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mercy
    -0.06
     yüzden
    -0.06
    ,r
    -0.06
    hx
    -0.06
     vše
    -0.06
     banners
    -0.06
    인데
    -0.06
    ابقه
    -0.06
    рош
    -0.06
     quien
    -0.06
    POSITIVE LOGITS
     Challenger
    0.07
    engl
    0.06
    Input
    0.06
    ้ม
    0.06
     Stars
    0.06
    inqu
    0.06
     undert
    0.06
    sent
    0.06
    ١
    0.06
     CPI
    0.06
    Act Density 0.031%

    No Known Activations