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

    Neuronpedia

    INDEX
    Explanations

    references to external sources, citations, or surveys

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

    references, figures, polls, and highs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.69
     ویکی‌پدی
    -0.64
     VizieR
    -0.61
    awaiter
    -0.61
    存于互联网档案馆
    -0.61
    ised
    -0.60
    ритори
    -0.58
    ]")]
    -0.57
    出版年
    -0.57
    ième
    -0.57
    POSITIVE LOGITS
    <bos>
    0.97
    mods
    0.69
     Mods
    0.66
    Docs
    0.64
    Mods
    0.63
    libs
    0.61
    Figs
    0.59
     Sims
    0.59
     mods
    0.59
    refs
    0.59
    Act Density 0.030%

    No Known Activations