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

    Neuronpedia

    INDEX
    Explanations

    ваться

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     principally
    -0.09
    ARE
    -0.08
     chiefly
    -0.08
    我是
    -0.07
     catering
    -0.07
    ithe
    -0.07
     যেমন
    -0.07
     பெய
    -0.07
     chauff
    -0.07
     DEM
    -0.07
    POSITIVE LOGITS
    !";↵
    0.10
     ಹಿಡ
    0.09
    $link
    0.09
     ongem
    0.09
     छोड़
    0.09
     पकड़
    0.08
     håller
    0.08
    !;↵
    0.08
     ұст
    0.08
     perder
    0.08
    Act Density 0.009%

    No Known Activations