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

    Neuronpedia

    INDEX
    Explanations

    mention of economic and health-related metrics or statistics

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

    economic costs and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.42
     đúng
    -0.27
     vuelto
    -0.27
    seitige
    -0.27
    Примітки
    -0.26
     jegy
    -0.26
     pulang
    -0.26
    Personendaten
    -0.25
     CreateTagHelper
    -0.25
    曖昧さ回避
    -0.25
    POSITIVE LOGITS
    المناصب
    0.71
    ロウィン
    0.65
    DockStyle
    0.61
     ویکی‌پدی
    0.59
    Бахар
    0.59
    <unused23>
    0.57
    <unused28>
    0.57
    <unused17>
    0.57
    [@BOS@]
    0.57
    <unused16>
    0.57
    Act Density 0.064%

    No Known Activations