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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мет
    -0.08
    .biz
    -0.07
     ได
    -0.07
     bidding
    -0.07
     Beth
    -0.06
    獲得
    -0.06
     настоя
    -0.06
     desperate
    -0.06
     primo
    -0.06
     ------------
    -0.06
    POSITIVE LOGITS
    dataTable
    0.07
     inputs
    0.07
    	Matrix
    0.06
     GCC
    0.06
     Revenge
    0.06
    VertexAttribArray
    0.06
    '))↵↵↵
    0.06
    urface
    0.06
    endimento
    0.06
     Tree
    0.06
    Act Density 0.002%

    No Known Activations