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

    Neuronpedia

    INDEX
    Explanations

    performing operations or CRUD commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    懈
    -0.75
    зец
    -0.75
    せば
    -0.75
     Tổng
    -0.74
    boleh
    -0.72
    Brains
    -0.72
     traduzione
    -0.71
    clerosis
    -0.71
    arnings
    -0.70
    Curios
    -0.70
    POSITIVE LOGITS
     operations
    3.72
     manipulation
    3.25
    manip
    3.00
     manipulations
    2.97
    operations
    2.92
     manipulating
    2.88
     manipulate
    2.88
    操作
    2.88
    Operations
    2.61
     Operations
    2.59
    Act Density 0.258%

    No Known Activations