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

    Neuronpedia

    INDEX
    Explanations

    if known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orderBy
    0.71
     세
    0.70
     Loyal
    0.70
     Māori
    0.67
     einzig
    0.66
    瀉
    0.66
     සහ
    0.65
     Quis
    0.64
     xảy
    0.64
    forEach
    0.63
    POSITIVE LOGITS
    [:
    1.05
     nil
    1.03
    (:
    0.99
    /#{
    0.99
    nil
    0.98
     ||=
    0.95
     {|
    0.94
    ::
    0.92
    Rails
    0.91
     *@
    0.91
    Act Density 0.000%

    No Known Activations