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

    Neuronpedia

    INDEX
    Explanations

    high activation levels in messaging or communication protocols

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    std
    -0.37
     Mon
    -0.35
    Mon
    -0.34
     Parac
    -0.33
     std
    -0.33
     network
    -0.31
    Co
    -0.30
    _
    -0.30
    fähig
    -0.30
    mon
    -0.30
    POSITIVE LOGITS
     المعيارى
    0.92
     незавершена
    0.90
     kasarigan
    0.83
    脚注の使い方
    0.82
     nakalista
    0.81
    MigrationBuilder
    0.79
     ویکی‌پدی
    0.78
     autorytatywna
    0.77
    GraphicsUnit
    0.75
     CreateTagHelper
    0.75
    Act Density 0.097%

    No Known Activations