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

    Neuronpedia

    INDEX
    Explanations

    completeness or fullness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %
    1.38
    {
    1.34
    ্দ্র
    1.34
    ை
    1.27
    )
    1.22
    are
    1.14
    $
    1.11
     важ
    1.09
    ro
    1.09
    .
    1.08
    POSITIVE LOGITS
    ний
    1.34
     كامل
    1.34
     lading
    1.24
    كامل
    1.21
     hoàn
    1.15
     Full
    1.14
     žiad
    1.13
     Complete
    1.10
    完整
    1.05
     Dill
    1.05
    Act Density 0.823%

    No Known Activations