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

    Neuronpedia

    INDEX
    Explanations

    Code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ليس
    -0.07
     Stephens
    -0.07
     Tür
    -0.06
     STDERR
    -0.06
     Ξ
    -0.06
    бас
    -0.06
     holland
    -0.06
    Als
    -0.06
    jadi
    -0.06
     Tes
    -0.06
    POSITIVE LOGITS
    .coroutines
    0.07
     अन
    0.06
     Poverty
    0.06
    Booking
    0.06
     рекомен
    0.06
    (isset
    0.06
    .home
    0.06
    _AUTO
    0.06
     Lep
    0.06
    .pickle
    0.06
    Act Density 0.392%

    No Known Activations