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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کام
    -0.07
     такая
    -0.07
     Що
    -0.07
    anced
    -0.07
     sunk
    -0.07
    [*
    -0.07
     Emails
    -0.06
    まれ
    -0.06
     آغاز
    -0.06
     băng
    -0.06
    POSITIVE LOGITS
     broadband
    0.07
    financial
    0.07
     Besch
    0.07
     painfully
    0.06
     imz
    0.06
     employment
    0.06
     trợ
    0.06
    -full
    0.06
     yt
    0.06
    isé
    0.06
    Act Density 0.001%

    No Known Activations