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

    Neuronpedia

    INDEX
    Explanations

    modify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सद
    -0.07
    ократи
    -0.06
    zek
    -0.06
    ,application
    -0.06
    <Cell
    -0.06
    uffman
    -0.06
    .Comparator
    -0.06
    ительный
    -0.06
    (水
    -0.06
    庄
    -0.06
    POSITIVE LOGITS
     define
    0.07
     sentimental
    0.07
     garage
    0.07
    '>↵↵
    0.07
     SMALL
    0.06
    airie
    0.06
    _branch
    0.06
    <footer
    0.06
     specify
    0.06
     gắng
    0.06
    Act Density 0.001%

    No Known Activations