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

    Neuronpedia

    INDEX
    Explanations

    package mirrors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vá
    -0.08
     ધાર
    -0.08
     dy
    -0.07
     संदेश
    -0.07
    .messages
    -0.07
     메시
    -0.07
     consign
    -0.07
     Dy
    -0.07
    masının
    -0.07
     निर्णय
    -0.07
    POSITIVE LOGITS
     Scholar
    0.09
    Africa
    0.09
     الجزائر
    0.09
    新疆
    0.08
    China
    0.08
    leetcode
    0.08
     Belgique
    0.08
    Alibaba
    0.08
     Africa
    0.08
     peanut
    0.08
    Act Density 0.002%

    No Known Activations