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

    Neuronpedia

    INDEX
    Explanations

    simplify or simplicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aqui
    0.40
     đây
    0.39
     هنا
    0.39
     ارشاد
    0.39
     ici
    0.39
     vite
    0.39
     njia
    0.39
    icie
    0.38
    Вот
    0.38
     بمع
    0.38
    POSITIVE LOGITS
     simplify
    0.57
     complexity
    0.53
     simplicity
    0.52
    simplify
    0.51
    complexity
    0.49
     complication
    0.49
    簡
    0.46
     simplifies
    0.46
     simplification
    0.46
     simpl
    0.45
    Act Density 0.031%

    No Known Activations