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

    Neuronpedia

    INDEX
    Explanations

    Creative writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     տեղեկատվ
    -0.10
     vork
    -0.09
    俗
    -0.09
     qvod
    -0.08
     Qatar
    -0.08
     газар
    -0.08
     պարզ
    -0.08
     ուշադր
    -0.08
     hormatly
    -0.08
     广益
    -0.08
    POSITIVE LOGITS
    ń
    0.08
     upstairs
    0.08
    eping
    0.08
    ense
    0.08
    锋
    0.08
    arbeiter
    0.08
    %^
    0.08
     ethic
    0.08
    ाच्या
    0.08
     downstairs
    0.08
    Act Density 0.058%

    No Known Activations