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

    Neuronpedia

    INDEX
    Explanations

    basic backtesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fl
    0.54
    é
    0.48
    0.46
    UA
    0.46
    गिरी
    0.46
    샀
    0.45
     販売
    0.45
    URE
    0.44
     sw
    0.44
     ड्रा
    0.44
    POSITIVE LOGITS
    য
    0.41
    涳
    0.41
    லோச
    0.41
    ξεις
    0.41
     monolayers
    0.41
    vés
    0.40
     hồi
    0.40
    favorites
    0.40
    Extent
    0.40
     وذلك
    0.40
    Act Density 0.002%

    No Known Activations