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

    Neuronpedia

    INDEX
    Explanations

    art, Conservation, Day, LIFESTAGE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    젬
    1.08
     modular
    1.06
    ג
    1.02
     Ж
    1.01
    ଟି
    1.00
    偃
    0.98
    navi
    0.96
     appelé
    0.96
     tampilan
    0.94
     neckline
    0.94
    POSITIVE LOGITS
    ക്ക്
    1.04
    ക്ക്‌
    1.02
     fare
    0.97
     commitments
    0.97
     Graffiti
    0.96
    ভিড
    0.95
     especiais
    0.95
    ために
    0.95
     मूल
    0.94
    Lime
    0.94
    Act Density 0.000%

    No Known Activations