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

    Neuronpedia

    INDEX
    Explanations

    leading alternative activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Could
    0.44
     August
    0.44
     Stocks
    0.44
     Brug
    0.44
     Harr
    0.43
    ู
    0.43
    рі
    0.43
     Kep
    0.43
     Dried
    0.43
    inary
    0.42
    POSITIVE LOGITS
    стин
    0.48
     iniciativas
    0.45
    konto
    0.45
     работода
    0.44
     teorema
    0.44
     mixts
    0.44
    vista
    0.43
    colLast
    0.42
     blanditiis
    0.42
     contradict
    0.41
    Act Density 0.002%

    No Known Activations