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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nesta
    -0.08
    =data
    -0.07
     betray
    -0.07
     petroleum
    -0.06
     FAILED
    -0.06
     Už
    -0.06
    (Network
    -0.06
     unidentified
    -0.06
     overwhelming
    -0.06
     rapidly
    -0.06
    POSITIVE LOGITS
    виг
    0.07
    Section
    0.06
    barcode
    0.06
    Inspect
    0.06
     складу
    0.06
    Sidebar
    0.06
    /articles
    0.06
    แนว
    0.06
    _CIPHER
    0.06
    /framework
    0.06
    Act Density 0.012%

    No Known Activations