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

    Neuronpedia

    INDEX
    Explanations

    categories and terms related to various sectors and industries, especially in finance, education, and healthcare

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

    category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.61
     GenerationType
    -0.54
    帖最后由
    -0.53
     HFILL
    -0.50
    تقاوى
    -0.50
    optionalTypeArgs
    -0.49
    Jîn
    -0.48
    SourceChecksum
    -0.47
     mergeFrom
    -0.46
    principalColumn
    -0.45
    POSITIVE LOGITS
     houſe
    0.59
     Houſe
    0.55
     myſelf
    0.54
     Diſ
    0.51
     Eſ
    0.48
     themſelves
    0.47
     autorytatywna
    0.47
     Inſ
    0.46
     faſt
    0.46
     ſtate
    0.46
    Act Density 0.018%

    No Known Activations