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

    Neuronpedia

    INDEX
    Explanations

    indicators of statistical significance and comparisons in scientific research

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

    foreign or technical names

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects numeric tokens and digit-heavy sequences (numbers, figure/section/table indices and other multi-digit numeric strings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     net
    -0.36
    net
    -0.34
     inspect
    -0.32
     trust
    -0.32
     alter
    -0.32
    hh
    -0.31
    ellige
    -0.31
    her
    -0.31
     h
    -0.31
     alt
    -0.31
    POSITIVE LOGITS
     disambiguazione
    0.77
     NSCoder
    0.75
     autorytatywna
    0.75
    httphttps
    0.73
    Datuak
    0.73
     виправивши
    0.71
    AutoModerator
    0.70
    ConstraintMaker
    0.70
     يتيمه
    0.66
     pinulongan
    0.66
    Act Density 1.015%

    No Known Activations