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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sett
    -0.08
    ViewSet
    -0.07
    house
    -0.07
     counts
    -0.07
     visite
    -0.07
    金银
    -0.07
     mez
    -0.07
     tuples
    -0.07
     happily
    -0.06
     disqualified
    -0.06
    POSITIVE LOGITS
    护照
    0.08
    erved
    0.07
    objc
    0.07
     צורך
    0.07
    تكلفة
    0.07
    (Resources
    0.07
    쉼
    0.07
    (PRO
    0.07
     parler
    0.07
     kle
    0.07
    Act Density 0.003%

    No Known Activations