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

    Neuronpedia

    INDEX
    Explanations

    code ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ６
    0.73
    Need
    0.71
     каждое
    0.71
     six
    0.69
     ६
    0.69
     шесть
    0.66
     Wednesdays
    0.65
    6
    0.65
     unambiguously
    0.65
     Need
    0.64
    POSITIVE LOGITS
    idi
    0.69
    лиги
    0.68
    ദീ
    0.67
     inflater
    0.64
     Visibility
    0.64
    тами
    0.64
    ষ্টিত
    0.62
    șt
    0.62
     intimated
    0.61
    παι
    0.61
    Act Density 0.065%

    No Known Activations