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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    耰
    -0.07
     Nhất
    -0.07
    語
    -0.07
    -cloud
    -0.07
     Harbor
    -0.07
    ,'']]],↵
    -0.07
    .method
    -0.07
    .Cast
    -0.07
    returnValue
    -0.06
     rộng
    -0.06
    POSITIVE LOGITS
    haar
    0.07
     interés
    0.07
    덴
    0.07
    rowData
    0.07
    ائح
    0.07
    initial
    0.07
    .contents
    0.07
    _easy
    0.07
    scheduler
    0.07
     Indiana
    0.07
    Act Density 0.001%

    No Known Activations