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

    Neuronpedia

    INDEX
    Explanations

    questions about duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    祹
    0.41
     مشارکت
    0.38
     частей
    0.37
     WHICH
    0.36
     Генера
    0.36
     nke
    0.36
    {~
    0.35
    THIS
    0.35
    際
    0.35
    Տ
    0.35
    POSITIVE LOGITS
     befind
    0.40
     untimely
    0.39
     ob
    0.39
    inot
    0.39
     forego
    0.38
     owes
    0.38
     nom
    0.38
    lio
    0.38
     wants
    0.37
     erg
    0.36
    Act Density 0.000%

    No Known Activations