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

    Neuronpedia

    INDEX
    Explanations

    consumption and resource usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পাবেন
    0.74
    aph
    0.71
    RetResult
    0.67
    看向
    0.67
     reunification
    0.66
     logrado
    0.66
    笑顔
    0.66
    再現
    0.66
    maat
    0.65
     Achieve
    0.65
    POSITIVE LOGITS
     consumption
    3.51
     consume
    3.37
     consuming
    3.25
     Consumption
    3.15
     consumes
    3.11
    consumption
    3.08
    Consumption
    3.03
     consumo
    2.97
     consumed
    2.90
     Consume
    2.87
    Act Density 0.528%

    No Known Activations