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

    Neuronpedia

    INDEX
    Explanations

    ценовой, цены, ценой

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рке
    0.39
    ິນ
    0.38
     Fie
    0.37
    cerning
    0.37
     коле
    0.36
     Кан
    0.36
    బ్ర
    0.35
     Concerning
    0.35
    ক্ষা
    0.35
    銅
    0.35
    POSITIVE LOGITS
    ena
    0.44
     Syd
    0.42
    elta
    0.39
    rijven
    0.39
     Exxon
    0.38
     novelty
    0.38
    лия
    0.38
    dad
    0.38
     litter
    0.38
    enez
    0.38
    Act Density 0.001%

    No Known Activations