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

    Neuronpedia

    INDEX
    Explanations

    simplify and rewrite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обеспечение
    0.46
     oraș
    0.46
    建设
    0.46
    قافة
    0.46
    قه
    0.45
     pabbaj
    0.45
     zapewn
    0.45
     giá
    0.44
    úd
    0.44
     diadakan
    0.44
    POSITIVE LOGITS
    simplify
    0.87
     simplify
    0.83
     simplification
    0.82
     simplifying
    0.81
    Simplify
    0.77
     Simplify
    0.77
     simplifies
    0.75
     simpl
    0.69
    Simpl
    0.69
     Simplifying
    0.64
    Act Density 0.084%

    No Known Activations