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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNIVERS
    -0.07
    _green
    -0.07
    Uuid
    -0.07
    ิตร
    -0.06
    :]
    -0.06
    plers
    -0.06
     Flower
    -0.06
    меч
    -0.06
     apar
    -0.06
    (download
    -0.06
    POSITIVE LOGITS
     Changes
    0.07
     migrant
    0.07
     stone
    0.07
     QR
    0.06
     cellspacing
    0.06
     und
    0.06
     laws
    0.06
    düm
    0.06
     efficient
    0.06
     generosity
    0.06
    Act Density 0.076%

    No Known Activations