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

    Neuronpedia

    INDEX
    Explanations

    structures and components of documentation or technical specifications

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

    Markdown section headers

    np_acts-logits-general · gemini-2.0-flash

    documentation headings and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.69
    SOUNDBITE
    -0.68
     EconPapers
    -0.67
    aarrggbb
    -0.67
     springfox
    -0.66
    verwijspagina
    -0.65
     aDecoder
    -0.65
    Sucesor
    -0.64
     незавершена
    -0.63
     &___
    -0.63
    POSITIVE LOGITS
    <eos>
    0.77
    <h2>
    0.72
    <h3>
    0.65
    </h3>
    0.58
    <h4>
    0.57
    ↵↵↵
    0.51
    ↵↵
    0.49
    </h2>
    0.49
    </tbody>
    0.48
    ↵↵↵↵↵
    0.47
    Act Density 0.099%

    No Known Activations