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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Мы
    0.40
    㧋
    0.39
    हमने
    0.38
    郤
    0.38
    Пре
    0.37
     используя
    0.37
    дон
    0.36
     провер
    0.35
    흙
    0.35
    Основ
    0.35
    POSITIVE LOGITS
     QSOs
    0.40
     indictment
    0.38
     waive
    0.38
     rodeo
    0.37
     layoffs
    0.36
    :'',
    0.36
     entre
    0.36
     cowboy
    0.35
     immig
    0.35
     homecoming
    0.35
    Act Density 0.016%

    No Known Activations