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

    Neuronpedia

    INDEX
    Explanations

    chemical components and their concentrations in various substances

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

    Percentage values

    np_acts-logits-general · gemini-2.0-flash

    percentage by weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.62
     distanciation
    -0.55
     magasiner
    -0.54
    alquiler
    -0.54
     дописавши
    -0.53
     Zwer
    -0.48
     kvadrat
    -0.48
    __*/
    -0.48
     złotych
    -0.47
    alanx
    -0.47
    POSITIVE LOGITS
     content
    1.18
     Content
    0.99
    content
    0.97
    Content
    0.94
     composition
    0.90
     contents
    0.90
     CONTENT
    0.89
     conteúdo
    0.89
    CONTENT
    0.88
    ontent
    0.87
    Act Density 0.829%

    No Known Activations