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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    倫
    -0.07
    產
    -0.07
    产
    -0.07
    òn
    -0.07
     días
    -0.07
    tered
    -0.06
     DG
    -0.06
     independence
    -0.06
    系列
    -0.06
     peuvent
    -0.06
    POSITIVE LOGITS
    (Parameter
    0.06
    Spr
    0.06
    arnings
    0.06
     giveaway
    0.06
     tired
    0.06
     Restr
    0.06
     требуется
    0.06
     Millennials
    0.06
     ging
    0.06
    =__
    0.06
    Act Density 0.000%

    No Known Activations