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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.55
     sparing
    0.52
     t
    0.51
    na
    0.49
     dune
    0.49
     $
    0.48
     forbidding
    0.48
    د
    0.48
     Interference
    0.46
     "
    0.46
    POSITIVE LOGITS
    矜
    0.52
    startDate
    0.52
     geliş
    0.51
    ;;)
    0.51
    นะคะ
    0.51
    GIN
    0.49
    feier
    0.49
    फ़ी
    0.49
    luent
    0.49
    )**
    0.49
    Act Density 0.016%

    No Known Activations