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

    Neuronpedia

    INDEX
    Explanations

    AP Press

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matric
    -0.08
     discerning
    -0.08
     administra
    -0.08
     grunt
    -0.07
     ferv
    -0.07
    Ave
    -0.07
     পূ
    -0.07
     motions
    -0.07
    Barrier
    -0.07
     fosters
    -0.07
    POSITIVE LOGITS
    新闻
    0.09
    文章
    0.08
    标题
    0.08
     ಸುದ್ದಿ
    0.08
     titled
    0.08
     સમાચાર
    0.08
     ಸುದ್ದ
    0.08
    _cached
    0.08
    《
    0.08
    の記事
    0.08
    Act Density 0.073%

    No Known Activations