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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    никами
    -0.07
    zeń
    -0.07
    才
    -0.06
     多
    -0.06
    *y
    -0.06
     ump
    -0.06
    (PDO
    -0.06
    茶
    -0.06
     코로나
    -0.06
    EObject
    -0.06
    POSITIVE LOGITS
    提示
    0.07
    /portfolio
    0.06
     Baz
    0.06
     Pact
    0.06
     Bethlehem
    0.06
    Australia
    0.06
    ibil
    0.06
    UPS
    0.06
    Argentina
    0.06
    vail
    0.06
    Act Density 0.020%

    No Known Activations