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

    Neuronpedia

    INDEX
    Explanations

    -type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ritual
    -0.08
     js
    -0.07
    ACTIVE
    -0.07
     professionnel
    -0.06
    ฉ
    -0.06
     لكن
    -0.06
    虽然
    -0.06
     Marilyn
    -0.06
     Bobby
    -0.06
    })
↵
    -0.06
    POSITIVE LOGITS
     carc
    0.06
    ând
    0.06
    atat
    0.06
     arbe
    0.06
    urchased
    0.06
    岸
    0.06
    prav
    0.06
    Consum
    0.06
     invo
    0.06
     مربع
    0.06
    Act Density 0.001%

    No Known Activations