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

    Neuronpedia

    INDEX
    Explanations

    specific names and proper nouns

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

    Proper names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.35
     rempliss
    -0.35
    RenderAtEndOf
    -0.34
    awtextra
    -0.32
     extra
    -0.32
    .
    -0.31
    AntiForgeryToken
    -0.30
    +#+#
    -0.29
     trhu
    -0.29
     yön
    -0.28
    POSITIVE LOGITS
     Reſ
    0.67
     Monfieur
    0.64
     Majefty
    0.63
    ]--;
    0.60
     ſever
    0.58
     ویکی‌پدی
    0.58
    ffions
    0.57
     Verſ
    0.56
     Theſe
    0.56
    ſelf
    0.56
    Act Density 0.140%

    No Known Activations