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

    Neuronpedia

    INDEX
    Explanations

    sustainability and ESG initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    系统的
    0.40
    用戶
    0.39
    壟
    0.39
    自动化
    0.38
     system
    0.38
     บท
    0.38
     Security
    0.38
     آز
    0.38
     보안
    0.37
    系统
    0.37
    POSITIVE LOGITS
     initiatives
    1.09
     iniciativas
    0.91
     Initiatives
    0.91
     commitments
    0.90
     agenda
    0.85
     agendas
    0.84
     efforts
    0.79
    agenda
    0.78
     credentials
    0.73
     commitment
    0.71
    Act Density 0.014%

    No Known Activations