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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Snow
    -0.06
     Rape
    -0.06
    Their
    -0.06
     api
    -0.06
    .Data
    -0.06
     Independence
    -0.06
     Prison
    -0.06
    閉
    -0.06
    Summary
    -0.06
     feminism
    -0.06
    POSITIVE LOGITS
    athed
    0.06
     채용
    0.06
     setActive
    0.06
    สำ
    0.06
    }${
    0.06
     Kraft
    0.06
     INCIDENTAL
    0.06
     врем
    0.06
    ">-->↵
    0.06
    ]--;↵
    0.06
    Act Density 0.069%

    No Known Activations