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

    Neuronpedia

    INDEX
    Explanations

    legal, ending with "ors"/"enor"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elena
    -0.07
     Ray
    -0.06
     Server
    -0.06
     Walt
    -0.06
    سانی
    -0.06
    ayla
    -0.06
     ім
    -0.06
    _layers
    -0.06
     Credits
    -0.06
     Tesla
    -0.06
    POSITIVE LOGITS
    υπ
    0.08
    íc
    0.07
     Tổng
    0.07
     provoz
    0.06
    ThreadId
    0.06
     svaz
    0.06
     heraus
    0.06
    valuation
    0.06
     applicationContext
    0.06
    ้าต
    0.06
    Act Density 0.002%

    No Known Activations