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

    Neuronpedia

    INDEX
    Explanations

    care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Portfolio
    -0.07
     Table
    -0.07
     plurality
    -0.06
    太久
    -0.06
    xAB
    -0.06
     Inspector
    -0.06
     bs
    -0.06
     нап
    -0.06
    Previous
    -0.06
    acc
    -0.06
    POSITIVE LOGITS
     gạo
    0.08
     kiến
    0.07
     importância
    0.07
     Hương
    0.07
    糒
    0.07
    emark
    0.07
    \Mapping
    0.07
     leftover
    0.07
    绿水
    0.06
    dın
    0.06
    Act Density 0.072%

    No Known Activations