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

    Neuronpedia

    INDEX
    Explanations

    code declarations and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     głos
    0.72
    <code>
    0.69
     Potomac
    0.62
     Instead
    0.62
    정이
    0.62
     oczy
    0.61
     สืบค้นเมื่อ
    0.60
    ということで
    0.59
     Moira
    0.59
    μος
    0.59
    POSITIVE LOGITS
     *
    4.04
    *
    3.50
     *$
    3.11
    -*
    3.10
     (*
    3.09
     \*
    3.08
    .*
    3.05
     *\
    3.01
     *(
    2.95
     *,
    2.95
    Act Density 0.124%

    No Known Activations