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

    Neuronpedia

    INDEX
    Explanations

    replaying in head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     новости
    0.55
     notícias
    0.54
    |_{
    0.53
     reactivity
    0.52
     afield
    0.52
     brisket
    0.52
     (
    0.52
     iure
    0.52
    (
    0.51
    ালে
    0.50
    POSITIVE LOGITS
    t
    0.76
    ne
    0.66
    č
    0.65
    end
    0.60
    ด
    0.59
    ř
    0.58
    ર
    0.56
    ou
    0.55
    Pokud
    0.55
     Kuala
    0.54
    Act Density 0.001%

    No Known Activations