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

    Neuronpedia

    INDEX
    Explanations

    Calculating markup percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kubernetes
    -0.08
     elusive
    -0.08
     kub
    -0.08
    KS
    -0.08
     Meditation
    -0.07
     Muk
    -0.07
     unravel
    -0.07
     Wester
    -0.07
    _uart
    -0.07
    _tuple
    -0.07
    POSITIVE LOGITS
    Markup
    0.11
     markup
    0.10
    markup
    0.08
    利润
    0.08
    出售
    0.08
     ratio
    0.08
    Ratio
    0.08
    _markup
    0.08
     dinero
    0.08
     precio
    0.08
    Act Density 0.005%

    No Known Activations