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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ографія
    -0.08
    Channels
    -0.07
    outube
    -0.07
    odium
    -0.06
    ูตร
    -0.06
    bia
    -0.06
    Auto
    -0.06
    Shield
    -0.06
     фото
    -0.06
    ?>"/>↵
    -0.06
    POSITIVE LOGITS
     And
    0.07
     and
    0.07
    ，并
    0.07
    HELP
    0.07
    _Get
    0.07
     hiç
    0.06
     und
    0.06
     AND
    0.06
     fikir
    0.06
     ş
    0.06
    Act Density 0.152%

    No Known Activations