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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions, particularly related to sums and products

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

    Mathematical summation or product operations

    np_acts-logits-general · gemini-2.0-flash

    sum and product notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    -0.59
     Plus
    -0.57
     "
    -0.53
     A
    -0.50
    ↵↵
    -0.50
    ’
    -0.50
     is
    -0.49
     par
    -0.49
     re
    -0.48
     $\
    -0.48
    POSITIVE LOGITS
    mybatisplus
    1.00
    tagHelperRunner
    0.98
    InSection
    0.92
     propOrder
    0.91
    ArrowToggle
    0.86
    NUMX
    0.86
     myſelf
    0.82
    AndEndTag
    0.80
    Попис
    0.80
     виправивши
    0.80
    Act Density 0.130%

    No Known Activations