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

    Neuronpedia

    INDEX
    Explanations

    sunlit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.72
    ad
    0.66
    ing
    0.66
    OS
    0.57
    ana
    0.55
    ă
    0.52
    is
    0.51
    ä
    0.51
     We
    0.51
    hi
    0.50
    POSITIVE LOGITS
    ك
    0.50
     dents
    0.46
    ↵
    0.43
    ような
    0.43
     بیا
    0.43
    ،
    0.43
     gaskets
    0.41
     yanı
    0.41
    、（
    0.41
     реаль
    0.41
    Act Density 0.000%

    No Known Activations