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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يست
    -0.07
     özellikle
    -0.07
    ede
    -0.07
    елем
    -0.06
    cps
    -0.06
     현대
    -0.06
     방문
    -0.06
     дія
    -0.06
     considerations
    -0.06
    (day
    -0.06
    POSITIVE LOGITS
    fone
    0.07
     performing
    0.07
     υπάρχουν
    0.07
    agr
    0.06
    cab
    0.06
     Wil
    0.06
     External
    0.06
     pratic
    0.06
    .Rad
    0.06
     rented
    0.06
    Act Density 0.019%

    No Known Activations