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

    Neuronpedia

    INDEX
    Explanations

    professional followed by contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.21
     والس
    1.15
    ാപാ
    1.07
    ningen
    1.04
    NavigationView
    0.99
    𝘴
    0.99
    gatt
    0.98
    aget
    0.97
    Ы
    0.97
    咙
    0.96
    POSITIVE LOGITS
    ように
    1.21
    িত্ব
    1.11
    人士
    1.10
    ので
    1.09
     footballer
    1.07
    Grade
    1.01
    хом
    0.98
     obligated
    0.98
    ization
    0.97
     Lon
    0.97
    Act Density 0.052%

    No Known Activations