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

    Neuronpedia

    INDEX
    Explanations

    converting to energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    素质
    0.54
    诡
    0.54
    违反
    0.51
     hinsichtlich
    0.50
    毁灭
    0.50
    学术
    0.49
    浈
    0.49
    名单
    0.49
    危险
    0.49
    职责
    0.48
    POSITIVE LOGITS
     energy
    0.89
     harnessing
    0.84
     harvesting
    0.81
     geothermal
    0.79
     hydropower
    0.77
     renewable
    0.72
     water
    0.71
     sustainably
    0.71
     sustainable
    0.70
     turbine
    0.70
    Act Density 0.082%

    No Known Activations