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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [attr
    -0.07
    Occurs
    -0.07
    ennie
    -0.07
    (import
    -0.07
    捻
    -0.07
    ному
    -0.07
    -parts
    -0.06
    配件
    -0.06
     setDescription
    -0.06
     marker
    -0.06
    POSITIVE LOGITS
    𝕙
    0.08
    网站
    0.07
    YouTube
    0.07
     höher
    0.07
    Managed
    0.07
     source
    0.07
    ün
    0.07
     Background
    0.07
     external
    0.06
    Magic
    0.06
    Act Density 0.003%

    No Known Activations