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

    Neuronpedia

    INDEX
    Explanations

    HTML header tags

    oai_token-act-pair · gemini-2.0-flash

    HTML and figures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    de
    -0.62
    ↵
    -0.54
    is
    -0.54
    N
    -0.53
    .
    -0.52
    err
    -0.50
    da
    -0.50
    next
    -0.48
     del
    -0.48
    '
    -0.48
    POSITIVE LOGITS
     متعلقه
    1.05
    Personendaten
    1.02
    MigrationBuilder
    0.97
    InjectAttribute
    0.91
    تقاوى
    0.90
    Geplaatst
    0.90
     EconPapers
    0.88
    ThroughAttribute
    0.87
    Datuak
    0.86
     تضيفلها
    0.86
    Act Density 0.216%

    No Known Activations