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

    Neuronpedia

    INDEX
    Explanations

    words, not tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بغیر
    0.52
     ქვე
    0.49
    ："
    0.46
    NETWORK
    0.46
    UMI
    0.45
    ఎల్
    0.44
    लीफ
    0.44
     توسیع
    0.44
    ಗರ
    0.43
     یو
    0.43
    POSITIVE LOGITS
     units
    0.50
     panels
    0.47
     takeaways
    0.46
     if
    0.45
     resources
    0.45
     snacks
    0.44
     components
    0.44
     boats
    0.44
     gill
    0.44
    isyen
    0.44
    Act Density 0.002%

    No Known Activations