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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns or names related to places, people, and organizations

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

    followed by "ham", "off", or similar fragments

    np_acts-logits-general · gemini-2.0-flash

    German surnames and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.97
    PerformLayout
    -0.78
    aarrggbb
    -0.78
    principalTable
    -0.74
    yntaxException
    -0.70
    contentLoaded
    -0.69
    istoitu
    -0.68
    erializer
    -0.68
    DockStyle
    -0.68
    HasAnnotation
    -0.67
    POSITIVE LOGITS
     sqlSession
    0.58
    ftance
    0.55
     mList
    0.54
     testSet
    0.52
    different
    0.52
    leſs
    0.52
     Efq
    0.51
    ftances
    0.51
     Different
    0.51
    Rhône
    0.50
    Act Density 0.395%

    No Known Activations