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

    Neuronpedia

    INDEX
    Explanations

    . your name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingenuity
    0.65
    вшим
    0.65
     steric
    0.64
     onshore
    0.63
    perturbative
    0.63
    finement
    0.60
    يديا
    0.59
     discernment
    0.59
     আমিন
    0.59
    rils
    0.58
    POSITIVE LOGITS
     Shopping
    1.32
    商品
    1.32
    Employee
    1.31
     Employees
    1.30
    Movie
    1.30
    employees
    1.30
    Employees
    1.30
    Movies
    1.29
     produtos
    1.28
     productos
    1.27
    Act Density 3.239%

    No Known Activations