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

    Neuronpedia

    INDEX
    Explanations

    terms related to governance and regulations

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

    ending in specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    adjective suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.79
     "..\..\..\
    -0.70
     ویکی‌پدی
    -0.67
    IsContent
    -0.63
     pinulongan
    -0.63
    :✨
    -0.60
    MessageTagHelper
    -0.59
    ніципалі
    -0.58
    帖最后由
    -0.57
    DockStyle
    -0.56
    POSITIVE LOGITS
    ous
    0.83
    된
    0.73
    able
    0.73
    uous
    0.70
    orous
    0.69
    적인
    0.68
    した
    0.68
    ourable
    0.66
    astic
    0.65
    ious
    0.65
    Act Density 0.513%

    No Known Activations