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

    Neuronpedia

    INDEX
    Explanations

    markers and delimiters used in code or structured data

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

    TeX/LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    brackets and macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.05
     AspNetCore
    -1.00
    ########.
    -0.98
     ―――――
    -0.97
     ་་
    -0.95
     незавершена
    -0.94
     виправивши
    -0.93
     كومونز
    -0.93
    setVerticalGroup
    -0.91
    TagMode
    -0.90
    POSITIVE LOGITS
    <eos>
    0.75
    ...
    0.73
    …
    0.63
    ↵↵
    0.61
    ↵
    0.59
    ....
    0.58
    ↵↵↵↵
    0.57
    ↵↵↵
    0.55
     ...
    0.54
    "
    0.53
    Act Density 0.832%

    No Known Activations