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

    Neuronpedia

    INDEX
    Explanations

    hacks and generators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    000
    -0.07
    herited
    -0.07
    .Equal
    -0.07
    laden
    -0.07
    362
    -0.06
    .buy
    -0.06
    Null
    -0.06
     grown
    -0.06
    099
    -0.06
    Esc
    -0.06
    POSITIVE LOGITS
     Bund
    0.06
     FileOutputStream
    0.06
     İzmir
    0.06
     영어
    0.06
    0.06
    .Framework
    0.06
    특별시
    0.06
     halfway
    0.06
     Мон
    0.06
    ebek
    0.06
    Act Density 0.112%

    No Known Activations