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

    Neuronpedia

    INDEX
    Explanations

    memory and space usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     эмоциона
    0.76
     научно
    0.74
     émotion
    0.74
     পরম্প
    0.73
     ә
    0.73
    দুর
    0.71
     दोहरा
    0.70
     emociones
    0.70
    ពណ៌
    0.70
    千年
    0.70
    POSITIVE LOGITS
     space
    2.77
    Space
    2.47
    space
    2.42
     Space
    2.41
     공간
    2.33
    空间
    2.28
     espacio
    2.27
     espaço
    2.23
    スペース
    2.19
     пространство
    2.15
    Act Density 0.680%

    No Known Activations