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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prices
    -0.06
    .called
    -0.06
     seus
    -0.06
     фас
    -0.06
    からない
    -0.06
     serializer
    -0.06
     greed
    -0.06
     QMap
    -0.06
    違
    -0.06
     Randolph
    -0.06
    POSITIVE LOGITS
    ilib
    0.07
    (){↵
    0.06
    _;↵↵
    0.06
     вой
    0.06
    obby
    0.06
     Roku
    0.06
    [--
    0.06
    ;\↵
    0.06
    urrency
    0.06
    -quality
    0.06
    Act Density 0.042%

    No Known Activations