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

    Neuronpedia

    INDEX
    Explanations

    arithmetic calculations with digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gosudarstvennyj
    0.33
     infrastrukt
    0.33
    ထား
    0.32
    लिंग
    0.31
    केमॉन
    0.31
     سبسڈی
    0.31
    archiwizowane
    0.31
     Tjiwarl
    0.31
    జర్
    0.30
     అధికారు
    0.30
    POSITIVE LOGITS
    0.38
    math
    0.33
     math
    0.32
     +
    0.31
     digits
    0.31
     and
    0.30
    0
    0.30
     sum
    0.30
    ா
    0.30
    Â
    0.30
    Act Density 0.232%

    No Known Activations