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

    Neuronpedia

    INDEX
    Explanations

    taxonomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =size
    -0.07
     Strange
    -0.07
     гот
    -0.07
     América
    -0.07
     áo
    -0.07
     '%'
    -0.07
    ち
    -0.07
    ustering
    -0.07
     Webcam
    -0.07
     Essentials
    -0.07
    POSITIVE LOGITS
    Tax
    0.08
    expected
    0.06
    .map
    0.06
     clay
    0.06
     Т
    0.06
     SSA
    0.06
    ↵
    0.06
     FIX
    0.06
     taxp
    0.06
     draft
    0.06
    Act Density 0.001%

    No Known Activations