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

    Neuronpedia

    INDEX
    Explanations

    city, date, or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    1.35
    or
    1.33
    it
    1.13
    ע
    1.06
    ad
    1.05
    in
    1.05
    om
    0.98
    as
    0.95
    ent
    0.95
    ag
    0.92
    POSITIVE LOGITS
    مدينة
    1.00
    ্লাহ
    0.98
    тка
    0.98
     ntawm
    0.98
    น
    0.96
    köz
    0.95
    beel
    0.94
    遌
    0.93
    सिल
    0.91
    ти
    0.91
    Act Density 0.032%

    No Known Activations