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

    Neuronpedia

    INDEX
    Explanations

    Turkish and English suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lob
    0.46
    ONLINE
    0.44
    lox
    0.42
    TRA
    0.41
    szak
    0.41
    lass
    0.39
    onyl
    0.39
    NETT
    0.39
    itt
    0.39
    online
    0.39
    POSITIVE LOGITS
    arda
    0.45
    arini
    0.43
    үү
    0.43
    ıdır
    0.43
    ərə
    0.41
    ardan
    0.41
    arı
    0.40
     ı
    0.39
    arın
    0.38
    اره
    0.37
    Act Density 0.004%

    No Known Activations