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

    Neuronpedia

    INDEX
    Explanations

    prices and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonatomic
    -0.08
     పంప
    -0.08
     ನೀ
    -0.07
     dren
    -0.07
     correctement
    -0.07
    赏
    -0.07
    (on
    -0.07
     hele
    -0.07
     bekend
    -0.07
     noisy
    -0.07
    POSITIVE LOGITS
     again
    0.09
    again
    0.09
     paikka
    0.08
    word
    0.08
     portray
    0.08
     profesionales
    0.08
     parola
    0.08
     весьма
    0.07
     vähän
    0.07
     professionals
    0.07
    Act Density 0.046%

    No Known Activations