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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Female
    -0.07
    美妆
    -0.07
    גיש
    -0.07
     IUser
    -0.07
     nas
    -0.07
     traction
    -0.07
    보험
    -0.06
    创新驱动
    -0.06
    Updated
    -0.06
     mosques
    -0.06
    POSITIVE LOGITS
    roman
    0.08
    ocolate
    0.07
    ARING
    0.07
    יכון
    0.07
    枘
    0.07
    vice
    0.07
    يلة
    0.07
    chosen
    0.07
    arto
    0.07
    loi
    0.06
    Act Density 0.012%

    No Known Activations