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

    Neuronpedia

    INDEX
    Explanations

    references to news reports and journalistic sources

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

    BBC News

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schluss
    -0.41
    IUrlHelper
    -0.38
     berjalan
    -0.38
     berdiri
    -0.38
     hidupnya
    -0.37
     tensão
    -0.36
    RenderAtEndOf
    -0.36
     Ursprung
    -0.36
     thereto
    -0.35
    engg
    -0.34
    POSITIVE LOGITS
    httphttps
    0.56
    Tembelea
    0.53
    цездатний
    0.50
     BBC
    0.49
    BBC
    0.47
    >`;
    0.44
     uſ
    0.44
    XmlType
    0.43
    ----</
    0.43
     ſever
    0.43
    Act Density 0.018%

    No Known Activations