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

    Neuronpedia

    INDEX
    Explanations

    engineering calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    明显
    -0.09
    受付
    -0.09
    突然
    -0.08
    形式
    -0.08
     tinnitus
    -0.08
     carinho
    -0.08
     느낌
    -0.08
     planet
    -0.08
     garante
    -0.08
    包装
    -0.08
    POSITIVE LOGITS
     centroid
    0.08
    0.08
     curing
    0.08
     cured
    0.08
    Buckets
    0.08
     Bombay
    0.08
     healed
    0.07
    gamma
    0.07
     gamma
    0.07
    paragraph
    0.07
    Act Density 0.011%
    No Known Activations