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

    Neuronpedia

    INDEX
    Explanations

    append, add, push

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.54
    čno
    0.54
    prove
    0.51
     power
    0.51
     Mor
    0.51
     Burn
    0.51
     prove
    0.50
    Burn
    0.49
    wick
    0.48
    held
    0.48
    POSITIVE LOGITS
     เพิ่ม
    1.02
    を追加
    1.01
    addItem
    0.92
     добав
    0.89
     добавля
    0.89
    เพิ่ม
    0.88
    newItem
    0.88
     adição
    0.87
     添加
    0.86
     дода
    0.86
    Act Density 0.452%

    No Known Activations