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

    Neuronpedia

    INDEX
    Explanations

    high-frequency function words and proper nouns in the text

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

    pronouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.40
     ffilm
    -0.40
     урна
    -0.38
    tidaknya
    -0.36
    ]--;
    -0.33
     perche
    -0.33
    besondere
    -0.32
    enity
    -0.32
     Wikimedijinoj
    -0.32
     worauf
    -0.32
    POSITIVE LOGITS
    rrggbb
    0.53
    省市镇
    0.52
     snippetHide
    0.50
    aarrggbb
    0.50
    webElement
    0.48
    modelBuilder
    0.46
    fromnode
    0.44
     שוליים
    0.44
     Ron
    0.44
    Tikang
    0.43
    Act Density 0.167%

    No Known Activations