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

    Neuronpedia

    INDEX
    Explanations

    route optimization and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    1.35
    t
    1.27
    s
    1.24
    ς
    1.24
    ן
    1.23
    ни
    1.15
    '
    1.11
    ના
    1.02
     البيان
    1.00
    2
    0.98
    POSITIVE LOGITS
    as
    1.28
    on
    1.26
    ن
    1.15
    al
    1.13
     have
    1.09
    )。
    1.07
    in
    1.02
     routes
    1.02
    )，
    0.98
    ᥣ
    0.97
    Act Density 0.011%

    No Known Activations