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

    Neuronpedia

    INDEX
    Explanations

    web page index default detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     når
    0.28
     अनाज
    0.28
     trùng
    0.27
     wären
    0.27
     légère
    0.26
     incroy
    0.26
    🥹
    0.25
    عند
    0.25
     siempre
    0.25
    >∈</
    0.25
    POSITIVE LOGITS
     page
    0.35
     paragraph
    0.32
    Page
    0.31
     페이지
    0.31
     Page
    0.30
    page
    0.30
     paragraphs
    0.29
     section
    0.29
     HTML
    0.28
     .
    0.27
    Act Density 0.023%

    No Known Activations