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

    Neuronpedia

    INDEX
    Explanations

    if conditions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.42
     ediyoruz
    0.42
     Curly
    0.41
    !।
    0.41
    Curly
    0.41
     аналоги
    0.41
     Callable
    0.41
     Kig
    0.40
    >();
    0.40
    引发
    0.40
    POSITIVE LOGITS
    Madrid
    0.45
     commande
    0.44
    quem
    0.42
    vés
    0.42
     of
    0.42
    hent
    0.42
    注文
    0.42
     jednot
    0.41
    asta
    0.41
    장의
    0.41
    Act Density 0.001%

    No Known Activations