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

    Neuronpedia

    INDEX
    Explanations

    get, obtains, retrieves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    จทย์
    0.41
     devra
    0.39
     került
    0.39
    newData
    0.39
     kellett
    0.38
    newParameter
    0.37
    വിധ
    0.37
    ارة
    0.36
     postup
    0.36
     Ideally
    0.36
    POSITIVE LOGITS
    获得
    0.93
     الحصول
    0.90
    取得
    0.90
     obtaining
    0.89
     получить
    0.87
     obter
    0.84
     узнать
    0.84
    obtained
    0.83
    を取得
    0.83
     получения
    0.83
    Act Density 0.100%

    No Known Activations