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

    Neuronpedia

    INDEX
    Explanations

    life and eternity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ण्ट
    0.38
     educational
    0.35
    裡的
    0.34
    ပေ
    0.33
     देखील
    0.33
     обнару
    0.33
     presented
    0.33
     greeted
    0.33
     engulfed
    0.32
     strapped
    0.32
    POSITIVE LOGITS
     life
    0.55
     Life
    0.55
    Life
    0.50
     LIFE
    0.49
     heaven
    0.45
     życiu
    0.45
     eternity
    0.44
     живота
    0.44
     жизнью
    0.43
    life
    0.43
    Act Density 0.016%

    No Known Activations