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

    Neuronpedia

    INDEX
    Explanations

    recipes and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loto
    -0.09
     탈
    -0.08
     enää
    -0.08
    since
    -0.08
    forced
    -0.08
     faction
    -0.07
    Trading
    -0.07
     flakes
    -0.07
    .ttf
    -0.07
     lotto
    -0.07
    POSITIVE LOGITS
     Vorge
    0.10
     saucepan
    0.10
     refriger
    0.09
    步骤
    0.09
     refrigeration
    0.08
    方法
    0.08
    開始
    0.08
    ним
    0.08
     methodology
    0.08
     方法
    0.08
    Act Density 0.057%

    No Known Activations