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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pháp
    -0.06
     GlobalKey
    -0.06
     WK
    -0.06
    (Schedulers
    -0.06
     AppState
    -0.06
    lesia
    -0.06
    .dismiss
    -0.06
    탕
    -0.06
     Silicon
    -0.06
     StringType
    -0.06
    POSITIVE LOGITS
     awaits
    0.07
    ایل
    0.07
    478
    0.07
    英語
    0.07
    ='%
    0.07
    .-
    0.07
    :Int
    0.07
    마다
    0.06
    azz
    0.06
    關
    0.06
    Act Density 0.128%

    No Known Activations