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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Redirect
    -0.08
    set
    -0.08
    .HorizontalAlignment
    -0.07
    мо
    -0.07
    uck
    -0.07
    数字
    -0.07
    家喻户
    -0.07
     Pip
    -0.07
    NE
    -0.07
    텅
    -0.07
    POSITIVE LOGITS
     Craft
    0.07
    ikk
    0.07
    丝绸
    0.07
    伊斯兰
    0.07
    kr
    0.07
     caffe
    0.07
    .week
    0.07
    浪漫
    0.07
     Separ
    0.07
    ece
    0.07
    Act Density 0.002%

    No Known Activations