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

    Neuronpedia

    INDEX
    Explanations

    fill in the blanks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hurricane
    -0.09
     وهو
    -0.08
     अचानक
    -0.08
     مفت
    -0.08
     cardiac
    -0.07
     itu
    -0.07
     приб
    -0.07
     aeros
    -0.07
     fumes
    -0.07
     قلب
    -0.07
    POSITIVE LOGITS
     заполн
    0.12
    填写
    0.11
     fills
    0.10
     rellen
    0.10
     filled
    0.10
     filling
    0.10
     Filling
    0.10
     ontbre
    0.10
     ingev
    0.10
     preench
    0.10
    Act Density 0.012%

    No Known Activations