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

    Neuronpedia

    INDEX
    Explanations

    seconds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     письмо
    -0.08
     Pale
    -0.07
     ,↵↵
    -0.07
     Bers
    -0.07
     Baylor
    -0.07
    -0.07
    ielle
    -0.07
    stag
    -0.07
    Dist
    -0.07
     좀
    -0.07
    POSITIVE LOGITS
     dankzij
    0.10
     chóng
    0.09
    できます
    0.09
     gracias
    0.09
     grâce
    0.09
    మే
    0.09
    aneously
    0.08
     dauern
    0.08
     ermöglichen
    0.08
     što
    0.08
    Act Density 0.026%
    No Known Activations