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

    Neuronpedia

    INDEX
    Explanations

    Reports and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mileage
    -0.09
    Golf
    -0.08
    NF
    -0.08
    /includes
    -0.08
     jardins
    -0.08
     winery
    -0.08
    Mess
    -0.08
    drink
    -0.07
     golf
    -0.07
     premises
    -0.07
    POSITIVE LOGITS
     Weighted
    0.11
     weighted
    0.10
     averaged
    0.10
     标签
    0.09
    Weighted
    0.09
     বাংলা
    0.08
    weighted
    0.08
     minorities
    0.08
    指标
    0.08
     معیار
    0.08
    Act Density 0.001%

    No Known Activations