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

    Neuronpedia

    INDEX
    Explanations

    code, data, numbers, foreign script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desesper
    0.33
     nouveaux
    0.32
     inconce
    0.32
     lumière
    0.31
     futur
    0.31
     vehement
    0.31
     cadáver
    0.31
     semblables
    0.29
     fondamental
    0.29
     nawet
    0.28
    POSITIVE LOGITS
     ৬
    0.34
     మూడు
    0.33
     ৩
    0.32
    6
    0.29
    指定
    0.29
     তিনটি
    0.29
     जानकारी
    0.28
     ৪
    0.27
     セ
    0.27
    getCql
    0.27
    Act Density 0.176%

    No Known Activations