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

    Neuronpedia

    INDEX
    Explanations

    directly against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    病
    0.94
    Zulu
    0.89
    police
    0.87
    病的
    0.85
     Everybody
    0.81
     nạn
    0.81
     Smaller
    0.81
     nursing
    0.81
    init
    0.79
     eğer
    0.79
    POSITIVE LOGITS
    йс
    0.80
    havam
    0.79
     выполнять
    0.78
     вышел
    0.76
     входит
    0.75
     линии
    0.74
    满足
    0.74
     выполнить
    0.74
     WTO
    0.74
     противоре
    0.73
    Act Density 0.311%

    No Known Activations