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

    Neuronpedia

    INDEX
    Explanations

    URLs and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gluc
    0.29
     Zeb
    0.29
     cuánto
    0.28
     eut
    0.27
     Hepat
    0.26
     clínico
    0.26
     Cx
    0.26
     tâm
    0.26
     arth
    0.26
     Clermont
    0.26
    POSITIVE LOGITS
     مذکور
    0.41
    后者
    0.34
     appunto
    0.31
    ฯ
    0.30
    भीत
    0.30
     tersebut
    0.29
    said
    0.29
    Label
    0.29
    İR
    0.29
    गित
    0.28
    Act Density 0.383%

    No Known Activations