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

    Neuronpedia

    INDEX
    Explanations

    Test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pyl
    -0.07
    (Card
    -0.07
    ounge
    -0.07
     ngắn
    -0.06
    (fl
    -0.06
     rocked
    -0.06
    Market
    -0.06
    (slug
    -0.06
    idores
    -0.06
     cram
    -0.06
    POSITIVE LOGITS
    @Test
    0.07
    TestMethod
    0.07
    uyordu
    0.07
     PLAY
    0.06
    들과
    0.06
     impass
    0.06
     spokeswoman
    0.06
    _Success
    0.06
     Toro
    0.06
    öffent
    0.06
    Act Density 0.002%

    No Known Activations