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

    Neuronpedia

    INDEX
    Explanations

    кие

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     эксперт
    -0.09
     fique
    -0.09
     отзыв
    -0.08
     Stanton
    -0.08
    imore
    -0.08
     cheers
    -0.08
     fico
    -0.08
    (Stack
    -0.07
     explores
    -0.07
     используется
    -0.07
    POSITIVE LOGITS
     pared
    0.10
     minimalist
    0.09
     cripple
    0.09
     packaged
    0.09
     empa
    0.08
     elongated
    0.08
     reduced
    0.08
     dein
    0.08
     impover
    0.08
     economical
    0.08
    Act Density 0.003%

    No Known Activations