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

    Neuronpedia

    INDEX
    Explanations

    travel departure signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enter
    0.57
     entering
    0.52
     enters
    0.52
     input
    0.49
    entering
    0.49
    enter
    0.48
    Enter
    0.48
    input
    0.47
     Enter
    0.46
     Entering
    0.45
    POSITIVE LOGITS
    Departure
    1.23
     Depart
    1.17
     Departure
    1.17
     departure
    1.16
    Depart
    1.06
     depart
    1.05
     departures
    1.05
    departure
    1.05
     departed
    0.99
     departing
    0.98
    Act Density 0.003%

    No Known Activations