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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fieldType
    -0.07
    _parameter
    -0.06
     sitios
    -0.06
    484
    -0.06
    `(
    -0.06
     Scho
    -0.06
     RANGE
    -0.06
     раск
    -0.06
     произош
    -0.06
     только
    -0.06
    POSITIVE LOGITS
     {}\
    0.07
    ,path
    0.07
     Pack
    0.06
    esso
    0.06
    ,k
    0.06
    .blog
    0.06
    ,response
    0.06
    __↵↵
    0.06
    웨어
    0.06
    σμού
    0.06
    Act Density 0.002%

    No Known Activations