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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -field
    -0.08
     employs
    -0.08
    _field
    -0.07
     конкурент
    -0.07
     incurred
    -0.07
    _UPDATE
    -0.07
     inning
    -0.07
     సంక
    -0.07
     comprises
    -0.07
    -selection
    -0.07
    POSITIVE LOGITS
     людзей
    0.10
     خلکو
    0.10
     Rasmussen
    0.09
     людей
    0.09
     ماڻهن
    0.09
     ხალხ
    0.09
     մարդկանց
    0.09
    Jets
    0.09
     mensen
    0.09
     lidí
    0.09
    Act Density 0.004%

    No Known Activations