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

    Neuronpedia

    INDEX
    Explanations

    revolution, people, national identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.05
     Theſe
    -0.93
     Jefus
    -0.89
     Eſ
    -0.87
     myſelf
    -0.86
     Monfieur
    -0.85
    RegressionTest
    -0.83
    jooq
    -0.83
    Autoritní
    -0.82
     houſe
    -0.82
    POSITIVE LOGITS
    ↵↵
    0.62
    .
    0.54
    kun
    0.47
     =
    0.46
    \
    0.45
     (
    0.45
    >
    0.45
     LAR
    0.45
    lu
    0.44
    han
    0.43
    Act Density 0.170%

    No Known Activations