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

    Neuronpedia

    INDEX
    Explanations

    gerunds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‌ی
    2.25
    ’
    2.19
    ings
    2.08
    ‌ای
    2.05
    kannya
    2.05
    ️
    1.95
     habido
    1.95
     dotycz
    1.92
    ‌تر
    1.86
     scarring
    1.84
    POSITIVE LOGITS
    ส์
    2.58
    ع
    2.56
    ly
    2.38
    ش
    2.13
    մ
    2.11
    他
    2.05
    นา
    2.02
    redients
    2.00
    ن
    1.91
    то
    1.90
    Act Density 1.334%

    No Known Activations