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

    Neuronpedia

    INDEX
    Explanations

    physics explanations, exceptions, and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我知道
    0.49
    figuration
    0.45
     wished
    0.43
    人
    0.42
    Ᏹ
    0.42
     whiche
    0.42
    jobs
    0.41
    gladbach
    0.41
     thats
    0.41
    祁
    0.41
    POSITIVE LOGITS
     aan
    0.46
     Suzuki
    0.43
    作曲
    0.43
     kä
    0.43
     kø
    0.42
     kunj
    0.42
    🏪
    0.42
     家
    0.42
    సుకొ
    0.42
     русской
    0.41
    Act Density 0.000%

    No Known Activations