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

    Neuronpedia

    INDEX
    Explanations

    Centers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itories
    -0.07
     proxies
    -0.07
    沟
    -0.07
    ΟΡ
    -0.06
    学会
    -0.06
     Worm
    -0.06
     insights
    -0.06
    .Vertex
    -0.06
    (dm
    -0.06
    Summary
    -0.06
    POSITIVE LOGITS
    길
    0.07
     bif
    0.07
     portions
    0.06
    	Py
    0.06
     extinct
    0.06
              ↵
    0.06
     Bur
    0.06
     submar
    0.06
     locom
    0.06
     tem
    0.06
    Act Density 0.057%

    No Known Activations