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

    Neuronpedia

    INDEX
    Explanations

    societal structures and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     você
    0.94
     간단
    0.93
     நீங்கள்
    0.92
     మీరు
    0.91
     tweaks
    0.86
     Você
    0.84
     你
    0.83
    ที่คุณ
    0.82
     youll
    0.82
     ඔබට
    0.81
    POSITIVE LOGITS
     commensurate
    1.15
     thereby
    1.04
     undermines
    1.01
     sustainably
    1.00
     promotes
    0.98
    ociety
    0.94
     abroad
    0.92
     societies
    0.89
     threatens
    0.89
    harmed
    0.88
    Act Density 0.200%

    No Known Activations