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

    Neuronpedia

    INDEX
    Explanations

    forecasting speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Items
    0.77
     effectuées
    0.72
     UTIL
    0.71
    Oliver
    0.70
    LEE
    0.70
     newItem
    0.69
    GATE
    0.69
    GOING
    0.69
     Oliver
    0.69
    IZING
    0.68
    POSITIVE LOGITS
    कैसे
    0.75
     представляет
    0.73
    rikt
    0.72
     предлагает
    0.72
    personality
    0.72
    ための
    0.71
    ontaneous
    0.71
    đ
    0.71
     memperoleh
    0.71
     определяет
    0.71
    Act Density 0.001%

    No Known Activations