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

    Neuronpedia

    INDEX
    Explanations

    nationalities or locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     American
    -0.98
     Australian
    -0.89
    American
    -0.81
    Australian
    -0.73
    ,
    -0.62
     AMERICAN
    -0.56
     
    -0.56
     (
    -0.55
    .
    -0.54
     and
    -0.54
    POSITIVE LOGITS
    parsedMessage
    1.05
    Personendaten
    1.02
    ніципалі
    1.00
    UnknownFieldSet
    1.00
     defaultstate
    0.96
    WithIOException
    0.96
    MessageTagHelper
    0.94
    abestanden
    0.94
    expandindo
    0.93
     propOrder
    0.93
    Act Density 0.104%

    No Known Activations