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

    Neuronpedia

    INDEX
    Explanations

    for Generative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     강의
    0.43
     වල
    0.43
    ਾਰ
    0.41
     दा
    0.41
     olmak
    0.41
     başlat
    0.40
     Năm
    0.40
    Figura
    0.40
     İşte
    0.40
    encji
    0.39
    POSITIVE LOGITS
    Pipeline
    0.51
    kx
    0.46
    PLL
    0.46
    neat
    0.44
    Rail
    0.44
    UU
    0.43
    Ly
    0.43
    صاف
    0.41
    front
    0.41
     (
    0.41
    Act Density 0.001%

    No Known Activations