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

    Neuronpedia

    INDEX
    Explanations

    strategy used in contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    馴
    0.36
    规范
    0.36
     বিদ্ব
    0.35
     நிறு
    0.35
    ברו
    0.34
     מד
    0.34
    nombre
    0.34
    Попис
    0.33
     அற்புத
    0.33
    рович
    0.33
    POSITIVE LOGITS
     strategy
    4.13
     Strategy
    3.89
    Strategy
    3.80
     страте
    3.78
    strategy
    3.77
     strategi
    3.66
     strategie
    3.66
     stratégie
    3.64
     estrategia
    3.63
     стратегия
    3.63
    Act Density 0.129%

    No Known Activations