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

    Neuronpedia

    INDEX
    Explanations

    Turkish and Hungarian possessive suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aları
    0.84
    ları
    0.78
    leri
    0.76
    лары
    0.76
    maları
    0.72
    lari
    0.71
    uları
    0.66
    ileri
    0.66
    larımız
    0.65
    meleri
    0.65
    POSITIVE LOGITS
    ısını
    0.51
    ását
    0.50
    áját
    0.50
    ğinin
    0.49
    ését
    0.49
    気に
    0.47
    isine
    0.46
    ğini
    0.45
    isini
    0.44
    hishek
    0.43
    Act Density 0.001%

    No Known Activations