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

    Neuronpedia

    INDEX
    Explanations

    inserting or placing within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reconstru
    0.77
     acumul
    0.76
     compilation
    0.74
     भरपूर
    0.73
    絣
    0.73
     ущер
    0.73
     લખ
    0.73
     incessantly
    0.72
     मनोरंजन
    0.72
     ব্যাপক
    0.72
    POSITIVE LOGITS
     inserted
    1.67
     insertion
    1.57
     insert
    1.50
    insertion
    1.47
    inserted
    1.45
     inserting
    1.44
    Insertion
    1.42
    插入
    1.40
     Insert
    1.40
     Insertion
    1.38
    Act Density 0.169%

    No Known Activations