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

    Neuronpedia

    INDEX
    Explanations

    product style categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vať
    0.52
     도시
    0.50
    kében
    0.50
     የመጀመሪያ
    0.49
    光源
    0.48
     احمد
    0.47
     allemande
    0.46
     ιδια
    0.46
    ﹂
    0.46
     imprecise
    0.46
    POSITIVE LOGITS
    ,
    0.55
     bile
    0.54
    2
    0.54
    ara
    0.50
     je
    0.50
    ed
    0.49
     styles
    0.49
     male
    0.48
     bil
    0.46
     show
    0.45
    Act Density 0.004%

    No Known Activations