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

    Neuronpedia

    INDEX
    Explanations

    joining or leaving a job role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    얽
    0.52
     crux
    0.48
     trilogy
    0.47
    UPLOAD
    0.46
     hegemony
    0.45
     oligarch
    0.45
     cursed
    0.44
     sabbam
    0.44
     destru
    0.44
     essayer
    0.43
    POSITIVE LOGITS
     Joining
    0.68
     joining
    0.66
     Appointment
    0.62
     Appointments
    0.61
     appointment
    0.59
     новым
    0.59
     newcomer
    0.59
     যোগদান
    0.59
     ज्वाइन
    0.59
     назначен
    0.59
    Act Density 0.027%

    No Known Activations