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

    Neuronpedia

    INDEX
    Explanations

    protecting people and life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Problems
    0.36
    淘汰
    0.35
     boosting
    0.34
     Problem
    0.33
     Challenges
    0.33
     updates
    0.33
     নিখ
    0.33
     challenges
    0.33
     Error
    0.33
     Probleme
    0.33
    POSITIVE LOGITS
     integrity
    1.16
     integridad
    1.07
     sanctity
    1.03
     безопасность
    1.03
     здоровье
    1.01
     здоровья
    1.00
     bezpiecze
    1.00
     dignity
    0.98
     keselamatan
    0.98
     wellbeing
    0.98
    Act Density 0.058%

    No Known Activations