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

    Neuronpedia

    INDEX
    Explanations

    tells the story of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orifices
    0.45
     vorhand
    0.43
    这点
    0.41
     목적
    0.40
     plumes
    0.39
     orifice
    0.38
     morphisms
    0.38
    უნქ
    0.37
     의견
    0.37
    ercise
    0.37
    POSITIVE LOGITS
     story
    1.26
     داستان
    1.05
    故事
    1.05
     कहानी
    1.04
    的故事
    1.04
     이야기
    1.04
    讲述
    1.03
    story
    1.00
    เรื่อง
    1.00
     verhaal
    1.00
    Act Density 0.026%

    No Known Activations