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

    Neuronpedia

    INDEX
    Explanations

    drawing tools/libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绗
    -0.07
    Exclude
    -0.07
    熛
    -0.07
    妘
    -0.07
    (component
    -0.07
    펠
    -0.07
    蒿
    -0.07
    emean
    -0.07
        ↵    ↵    ↵
    -0.07
    三千
    -0.06
    POSITIVE LOGITS
     تست
    0.08
    .Products
    0.07
     Defendant
    0.07
    ístico
    0.07
    онт
    0.07
    params
    0.06
    \User
    0.06
     제
    0.06
    anners
    0.06
    icides
    0.06
    Act Density 0.039%

    No Known Activations