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

    Neuronpedia

    INDEX
    Explanations

    environmental impact and sustainability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wenn
    0.76
     وقتی
    0.68
     সমন্বয়
    0.66
    ιβ
    0.65
    icarbon
    0.62
    dyž
    0.61
     whatever
    0.61
     جب
    0.61
     بقدر
    0.60
     dés
    0.60
    POSITIVE LOGITS
    Environmental
    1.31
     environmental
    1.28
     Environmental
    1.19
    environmental
    1.18
     환경
    1.18
     ENVIRONMENTAL
    1.14
     Environment
    1.13
    Environment
    1.08
     environment
    1.06
    環境
    1.05
    Act Density 0.130%

    No Known Activations