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

    Neuronpedia

    INDEX
    Explanations

    Chris followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ysa
    0.93
    importance
    0.90
     reckoned
    0.88
     продов
    0.87
    Regards
    0.84
     नम
    0.83
     narod
    0.82
    Те
    0.82
    као
    0.81
    expect
    0.81
    POSITIVE LOGITS
    opher
    1.25
    itian
    0.92
     larger
    0.90
    チャン
    0.88
    ція
    0.87
     Froome
    0.83
    rüstung
    0.82
     Wren
    0.82
     Columbus
    0.81
     Cuomo
    0.80
    Act Density 0.002%

    No Known Activations