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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or symbolic notation elements

    np_acts-logits-general · gemini-2.0-flash

    math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     from
    -1.07
    from
    -0.80
     FROM
    -0.77
     dalla
    -0.72
     từ
    -0.68
    From
    -0.66
     $\
    -0.66
    ($_
    -0.65
     от
    -0.65
     From
    -0.65
    POSITIVE LOGITS
    SBATCH
    0.89
    CloseOperation
    0.81
    kháu
    0.80
     '\\;'
    0.79
    aarrggbb
    0.77
    MigrationBuilder
    0.76
     ویکی‌پدی
    0.75
    Personendaten
    0.74
     تضيفلها
    0.73
    Tikang
    0.72
    Act Density 1.281%

    No Known Activations