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

    Neuronpedia

    INDEX
    Explanations

    elements related to specific programming languages and their designed functionalities

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

    Specifically designed/intended

    np_acts-logits-general · gemini-2.0-flash

    specifically designed or intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.73
     الحره
    -0.70
    endphp
    -0.65
     ویکی‌پدیا
    -0.60
     onOptions
    -0.56
    󠁢
    -0.56
    čin
    -0.55
    ushchev
    -0.55
    rimônio
    -0.55
     Involved
    -0.54
    POSITIVE LOGITS
     designed
    2.41
    designed
    1.96
     intended
    1.93
     Designed
    1.85
     meant
    1.80
    Designed
    1.70
    intended
    1.68
    meant
    1.55
     dirancang
    1.52
     diseñado
    1.51
    Act Density 0.430%

    No Known Activations