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

    Neuronpedia

    INDEX
    Explanations

    describing context and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Implement
    0.50
     OLED
    0.47
     Purchase
    0.47
    ភ្ជាប់
    0.47
     Fintech
    0.47
     QuickBooks
    0.46
     Startup
    0.46
     Discount
    0.45
     Zuckerberg
    0.45
     Alipay
    0.45
    POSITIVE LOGITS
     classific
    0.48
    hiv
    0.43
    ہر
    0.42
     comandante
    0.41
    ラジオ
    0.41
     পড়েন
    0.41
     obeyed
    0.40
     replete
    0.40
    ﺏ
    0.40
    remain
    0.39
    Act Density 0.004%

    No Known Activations