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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رأ
    -0.08
     buckets
    -0.07
    ádu
    -0.06
    :↵↵↵↵↵↵
    -0.06
     Fundamental
    -0.06
    	add
    -0.06
     Лю
    -0.06
     Channel
    -0.06
    πα
    -0.06
     sleeping
    -0.06
    POSITIVE LOGITS
     edu
    0.08
     مرب
    0.07
    figures
    0.06
    ność
    0.06
     UNSIGNED
    0.06
    leta
    0.06
    .requests
    0.06
     urlencode
    0.06
    мець
    0.06
    ję
    0.06
    Act Density 0.000%

    No Known Activations