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

    Neuronpedia

    INDEX
    Explanations

    strategies and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     criminally
    0.50
     nowadays
    0.44
     Unternehmens
    0.44
    haben
    0.44
     comorbidities
    0.44
     artikkel
    0.43
     დღ
    0.43
    چنین
    0.43
     Empresas
    0.42
     administrat
    0.41
    POSITIVE LOGITS
    尽量
    0.52
     চেষ্টা
    0.50
     전략
    0.50
     attempts
    0.49
     strategi
    0.49
    策略
    0.49
     strategies
    0.48
    巧妙
    0.48
    排列
    0.47
     Puzzle
    0.47
    Act Density 0.122%

    No Known Activations