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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     throughout
    0.92
     miejsce
    0.79
     firsthand
    0.74
    ີ
    0.73
     Throughout
    0.71
    ुक
    0.70
     sepanjang
    0.70
    chik
    0.70
    Throughout
    0.70
     подро
    0.69
    POSITIVE LOGITS
     이미지
    0.86
    ImageUrl
    0.84
     страницы
    0.83
     спект
    0.83
    电器
    0.83
     spectrum
    0.82
     spectra
    0.82
    ไฟล์
    0.80
    img
    0.78
    EVERY
    0.78
    Act Density 0.105%

    No Known Activations