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

    Neuronpedia

    INDEX
    Explanations

    the presence of text indicating authorship or ownership in a document

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

    Characters surrounding brackets or symbols

    np_acts-logits-general · gemini-2.0-flash

    author attribution or mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.86
    ChildScrollView
    -0.70
    endphp
    -0.68
    ...',
    -0.66
     Архивная
    -0.64
    ValueGenerated
    -0.63
    #,
    -0.63
    .');
    -0.62
    ...');
    -0.62
    .';
    -0.62
    POSITIVE LOGITS
     Anonymous
    0.75
     Administrator
    0.69
    Anonymous
    0.68
     admin
    0.68
     user
    0.67
     anonymous
    0.66
     Unknown
    0.63
    admin
    0.62
    user
    0.62
     Admin
    0.62
    Act Density 0.171%

    No Known Activations