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

    Neuronpedia

    INDEX
    Explanations

    expand, expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     levels
    1.16
     Levels
    1.15
    le
    1.12
     anemia
    1.09
    leştir
    1.04
    ch
    1.01
    leşt
    1.00
     wages
    0.98
     senha
    0.98
     dólares
    0.97
    POSITIVE LOGITS
     horizons
    1.35
    ্ধ
    1.29
    ্বিত
    1.28
    Expanding
    1.27
     polystyrene
    1.26
     waist
    1.18
     misi
    1.12
     ليش
    1.09
     Expansion
    1.07
    し
    1.06
    Act Density 0.041%

    No Known Activations