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

    Neuronpedia

    INDEX
    Explanations

    keywords related to software components and modules in code

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

    paths and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.88
     незавершена
    -0.86
    httphttps
    -0.76
    Хьажоргаш
    -0.75
    帖最后由
    -0.73
     ModelExpression
    -0.73
     kaarangay
    -0.72
    MessageOf
    -0.72
     EconPapers
    -0.71
    ьаж
    -0.69
    POSITIVE LOGITS
    .
    0.46
    <h1>
    0.44
     auparavant
    0.42
     Brenner
    0.41
     Fryer
    0.38
    作
    0.38
     Moore
    0.38
     infrastructure
    0.38
    ine
    0.38
     and
    0.37
    Act Density 0.018%

    No Known Activations