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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QUEST
    -0.07
     Бер
    -0.07
     Costume
    -0.07
    ([&
    -0.07
     ضمن
    -0.06
     Herbal
    -0.06
     smarty
    -0.06
    "]);↵↵
    -0.06
    580
    -0.06
    ('\\
    -0.06
    POSITIVE LOGITS
    itt
    0.07
    etes
    0.07
    arı
    0.06
    età
    0.06
     шт
    0.06
     inclu
    0.06
    share
    0.06
     ################################################################
    0.06
    δρα
    0.06
    _score
    0.06
    Act Density 0.319%

    No Known Activations