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

    Neuronpedia

    INDEX
    Explanations

    model response marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     외부
    0.37
     বিভিন্ন
    0.35
     ሌሎች
    0.35
     ವಿವಿಧ
    0.34
     ተጨማሪ
    0.33
     विभिन्न
    0.32
    외부
    0.32
     기존
    0.31
     የበለጠ
    0.31
     heatmap
    0.31
    POSITIVE LOGITS
     American
    0.35
    K
    0.33
     America
    0.33
     Canada
    0.33
     North
    0.32
    C
    0.31
    ↵
    0.29
    T
    0.29
     Canadian
    0.29
     Ireland
    0.28
    Act Density 0.189%

    No Known Activations