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

    Neuronpedia

    INDEX
    Explanations

    adding data or elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مص
    0.46
    EY
    0.46
     حاصل
    0.43
    वाई
    0.40
    stelling
    0.39
    serving
    0.38
    уро
    0.38
    インタビュー
    0.38
    Ј
    0.37
    ه
    0.37
    POSITIVE LOGITS
     добавля
    0.89
     添加
    0.87
    添加到
    0.85
     adding
    0.80
     Adding
    0.79
    添加
    0.77
     inserting
    0.75
    addElement
    0.75
     addItem
    0.75
    插入
    0.73
    Act Density 0.152%

    No Known Activations