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

    Neuronpedia

    INDEX
    Explanations

    tribal communities and societies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יה
    2.34
    ਮ
    2.02
     problematic
    2.00
     troublesome
    1.94
     mile
    1.86
     vile
    1.77
     ripening
    1.70
     spire
    1.70
    ਮੀ
    1.70
    сці
    1.68
    POSITIVE LOGITS
    i
    2.70
     Ее
    2.25
    ه
    2.13
    ی
    2.11
    م
    2.09
    kan
    1.99
     Дом
    1.92
    Image
    1.91
    correcto
    1.91
    es
    1.90
    Act Density 0.002%

    No Known Activations