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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures or information sources

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

    "According to"

    np_acts-logits-general · gemini-2.0-flash

    according to source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.69
    TagMode
    -0.64
    InjectAttribute
    -0.62
    principalTable
    -0.60
    醐
    -0.59
     LEYENDO
    -0.58
    
    -0.58
    KommentareTeilen
    -0.56
     للمعارف
    -0.56
    mappedBy
    -0.55
    POSITIVE LOGITS
     reports
    1.30
     records
    1.11
     documents
    1.04
     interviews
    1.01
     descriptions
    1.00
     accounts
    0.97
    reports
    0.93
     testimony
    0.90
     sources
    0.90
     documentation
    0.88
    Act Density 0.555%

    No Known Activations