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

    Neuronpedia

    INDEX
    Explanations

    show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Withdraw
    -0.06
    ouses
    -0.06
    CUDA
    -0.06
    "C
    -0.06
    До
    -0.06
    )">↵
    -0.06
    Parking
    -0.06
    second
    -0.06
     Sioux
    -0.06
    ‘
    -0.06
    POSITIVE LOGITS
     zprav
    0.07
     pů
    0.06
    ematics
    0.06
    กร
    0.06
     twink
    0.06
    mış
    0.06
     曰
    0.06
    \-
    0.06
     лег
    0.06
    .document
    0.06
    Act Density 0.013%

    No Known Activations