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

    Neuronpedia

    INDEX
    Explanations

    references to various cultures and their contributions

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

    culture and traditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geſch
    -0.65
    ConstraintMaker
    -0.62
    脚注の使い方
    -0.61
     noDo
    -0.60
    <unused79>
    -0.60
    <unused52>
    -0.60
    <unused8>
    -0.60
    <unused28>
    -0.60
    <unused3>
    -0.60
    [@BOS@]
    -0.60
    POSITIVE LOGITS
     culture
    0.61
     cultural
    0.53
     Culture
    0.48
    文化
    0.48
     traditions
    0.46
     cultures
    0.45
    culture
    0.44
     CULTURE
    0.43
     rodea
    0.41
     culturelle
    0.41
    Act Density 0.017%

    No Known Activations