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

    Neuronpedia

    INDEX
    Explanations

    arrival and welcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reusing
    0.43
     selles
    0.42
     unhappiness
    0.40
     nuclé
    0.39
     አይደለም
    0.39
    产量
    0.38
    algèbre
    0.38
    笉
    0.38
     unhappy
    0.37
    锵
    0.37
    POSITIVE LOGITS
     arrival
    0.99
     arrivals
    0.89
     Arrival
    0.88
    Welcome
    0.87
     Welcome
    0.87
     greeted
    0.85
     आगमन
    0.84
     도착
    0.83
     welcome
    0.82
     welcomed
    0.82
    Act Density 0.102%

    No Known Activations