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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dut
    -0.07
     duplicates
    -0.07
     sunset
    -0.07
    包括
    -0.07
     felicidade
    -0.07
     Exhibit
    -0.07
    <Props
    -0.07
     Skeleton
    -0.07
     grin
    -0.07
     verv
    -0.07
    POSITIVE LOGITS
     ster
    0.08
    osta
    0.08
    Hibernate
    0.07
    CHASE
    0.07
     fuite
    0.07
     poche
    0.07
     તાલ
    0.07
     Bumble
    0.07
    lle
    0.07
    .'.
    0.07
    Act Density 0.023%

    No Known Activations