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

    Neuronpedia

    INDEX
    Explanations

    difficulty, tracking, dates, purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏄
    0.48
    🎸
    0.45
    ql
    0.43
     খুলে
    0.43
     ಗೋ
    0.42
    لیل
    0.41
    ведите
    0.41
     мобиль
    0.40
    グレー
    0.40
    🔷
    0.40
    POSITIVE LOGITS
    ính
    0.48
    oran
    0.43
     목적
    0.43
     realism
    0.42
    resso
    0.42
     परम
    0.42
    Nun
    0.42
     Purposes
    0.41
     पार
    0.41
    orifice
    0.41
    Act Density 0.003%

    No Known Activations