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

    Neuronpedia

    INDEX
    Explanations

    complex clever fascinating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هستند
    0.17
     Điều
    0.16
    idiendo
    0.16
     mAbs
    0.16
     cosidd
    0.16
     wheelchairs
    0.16
     janë
    0.16
     chromosomes
    0.15
     lluvias
    0.15
     Whey
    0.15
    POSITIVE LOGITS
    ,
    0.22
     и
    0.20
    तम
    0.19
    ،
    0.19
     و
    0.18
     ו
    0.18
     albeit
    0.18
     affair
    0.18
     nhất
    0.17
     ביותר
    0.17
    Act Density 1.699%

    No Known Activations