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

    Neuronpedia

    INDEX
    Explanations

    UNESCO World Heritage site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    比较
    0.75
     eher
    0.73
     ஆரம்பித்த
    0.73
     comparação
    0.73
     särsk
    0.72
     ='
    0.71
     규칙
    0.71
    するとき
    0.70
     заранее
    0.70
    どうしても
    0.70
    POSITIVE LOGITS
    *
    0.71
     (!)
    0.70
     Heritage
    0.70
    rt
    0.68
    🏆
    0.67
    A
    0.66
    িতেছে
    0.64
    !!!
    0.63
    *.
    0.63
     (!
    0.63
    Act Density 0.002%

    No Known Activations