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

    Neuronpedia

    INDEX
    Explanations

    the presence of structured data or programming syntax elements

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

    Text after a period or a colon

    np_acts-logits-general · gemini-2.0-flash

    section headings and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.52
    ddar
    -0.45
     Rueda
    -0.45
     vu
    -0.45
    blestone
    -0.43
     cartier
    -0.43
    робнее
    -0.42
    </strong>
    -0.42
    тен
    -0.41
    </b>
    -0.41
    POSITIVE LOGITS
    IsContent
    1.04
     @"/
    0.91
    पया
    0.86
     ModelExpression
    0.85
     nahilalakip
    0.84
    الدراسه
    0.83
     صوتيه
    0.83
     surla
    0.82
    WebVitals
    0.81
    帖最后由
    0.80
    Act Density 0.023%

    No Known Activations