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

    Neuronpedia

    INDEX
    Explanations

    Buddha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yola
    -0.07
     swallowed
    -0.07
    (":/
    -0.07
    -loving
    -0.06
    (serv
    -0.06
     Par
    -0.06
     havoc
    -0.06
     guise
    -0.06
     крок
    -0.06
    ερ
    -0.06
    POSITIVE LOGITS
     Buddha
    0.16
     Budd
    0.09
     budd
    0.08
     استاندارد
    0.07
    佛
    0.07
     佛
    0.06
    255
    0.06
    edException
    0.06
     Bri
    0.06
     Fif
    0.06
    Act Density 0.002%

    No Known Activations