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

    Neuronpedia

    INDEX
    Explanations

    their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    1.17
    an
    1.06
    이었다
    1.00
    ა
    0.99
    ва
    0.97
    ը
    0.95
    in
    0.94
    ور
    0.93
    та
    0.91
    on
    0.90
    POSITIVE LOGITS
     Lordships
    1.08
     وبين
    0.90
    ก
    0.89
    EO
    0.83
     Δια
    0.82
    ELL
    0.81
    selves
    0.80
    מ
    0.80
     propio
    0.78
    یی
    0.78
    Act Density 2.633%

    No Known Activations