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

    Neuronpedia

    INDEX
    Explanations

    gift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    (at
    -0.06
    Ur
    -0.06
    Highlight
    -0.06
     sexkontakte
    -0.06
    riz
    -0.06
    PerPage
    -0.06
     ü
    -0.06
    继
    -0.06
    =my
    -0.06
    POSITIVE LOGITS
     Japan
    0.06
     ");↵↵
    0.06
     Tacoma
    0.06
    >'+↵
    0.06
     未
    0.06
     fortunate
    0.06
    ('/')[
    0.06
    olar
    0.06
     Prague
    0.06
     дія
    0.06
    Act Density 0.065%

    No Known Activations