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

    Neuronpedia

    INDEX
    Explanations

    PDF document links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aile
    0.50
     mariage
    0.49
     équipe
    0.46
     têm
    0.46
     municipio
    0.45
     personnage
    0.45
     recherche
    0.45
     rythme
    0.43
     échange
    0.43
    私たちは
    0.43
    POSITIVE LOGITS
     PDF
    0.45
     इसी
    0.42
    B
    0.40
     similarly
    0.40
    其他
    0.39
    lexer
    0.39
    pdfs
    0.39
    Document
    0.39
     PDFs
    0.38
    ↵
    0.38
    Act Density 0.001%

    No Known Activations