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

    Neuronpedia

    INDEX
    Explanations

    you're likely to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.19
    ung
    1.05
    ด์
    1.04
     chuck
    1.03
    一方面
    1.00
     Kug
    1.00
    DE
    0.99
    MIUM
    0.96
    لين
    0.95
    นั้น
    0.95
    POSITIVE LOGITS
    Пе
    1.10
    État
    1.02
    Você
    1.02
    ০
    1.01
    ৬
    1.01
    Peri
    0.97
    ০০
    0.97
     zelo
    0.97
    mole
    0.93
    ৪
    0.93
    Act Density 0.020%

    No Known Activations