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

    Neuronpedia

    INDEX
    Explanations

    telling stories and anecdotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oscillating
    0.43
     adjustable
    0.38
     المصطلح
    0.38
     argued
    0.37
     oscillations
    0.37
     inspected
    0.36
     parameters
    0.35
     സമ
    0.35
     অগ্রসর
    0.34
     utili
    0.34
    POSITIVE LOGITS
     stories
    2.48
    stories
    2.22
     Stories
    2.19
    Stories
    2.14
     story
    2.11
     racconto
    2.09
     STORIES
    2.09
     anecdotes
    2.03
    故事
    2.02
     storie
    2.02
    Act Density 0.040%

    No Known Activations