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

    Neuronpedia

    INDEX
    Explanations

    Sports articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mænd
    -0.07
     vej
    -0.07
     overst
    -0.07
     cd
    -0.07
     therapy
    -0.07
    avras
    -0.07
     männer
    -0.06
    venge
    -0.06
    .Exchange
    -0.06
    thermal
    -0.06
    POSITIVE LOGITS
    (..
    0.07
     Renderer
    0.07
     то
    0.07
     ).↵↵
    0.07
     Boolean
    0.06
    -books
    0.06
    -result
    0.06
    �始化
    0.06
    _limit
    0.06
     Kurds
    0.06
    Act Density 0.008%

    No Known Activations