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

    Neuronpedia

    INDEX
    Explanations

    Poland Polish language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Япо
    0.77
    ücklich
    0.73
     Collectively
    0.73
     nefarious
    0.71
     Anzeige
    0.71
    高性能
    0.71
     Hershey
    0.70
     japan
    0.70
     Federated
    0.69
    rinsic
    0.69
    POSITIVE LOGITS
     Polish
    2.18
    Polish
    2.00
     Poland
    1.85
    Poland
    1.79
     Slovak
    1.59
     Warsaw
    1.59
     Lithuanian
    1.56
     Kraków
    1.54
     Krakow
    1.52
     Polonia
    1.49
    Act Density 0.018%

    No Known Activations