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

    Neuronpedia

    INDEX
    Explanations

    locate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     definite
    -0.07
     wonders
    -0.07
    滨
    -0.07
    [var
    -0.07
     plains
    -0.07
    ريعة
    -0.07
    орон
    -0.07
     annum
    -0.07
     Funeral
    -0.07
     humanitarian
    -0.07
    POSITIVE LOGITS
     kiếm
    0.09
    不到
    0.08
     pinakam
    0.08
     кого
    0.08
     freelance
    0.07
     passenden
    0.07
     Kup
    0.07
    ଲ
    0.07
    定位
    0.07
     καλύτε
    0.07
    Act Density 0.062%

    No Known Activations