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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sikh
    -0.07
    .conv
    -0.07
     buses
    -0.07
    bdb
    -0.06
     pict
    -0.06
    ErrMsg
    -0.06
     Cups
    -0.06
     gelişim
    -0.06
     Parses
    -0.06
     wives
    -0.06
    POSITIVE LOGITS
    )(↵
    0.07
    )((
    0.06
    園
    0.06
     -↵
    0.06
    )>↵
    0.06
    γρά
    0.06
     गर
    0.06
    )}
    0.06
     CDC
    0.06
     نشر
    0.06
    Act Density 0.005%

    No Known Activations