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

    Neuronpedia

    INDEX
    Explanations

    oops, apologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atrium
    0.49
     verstehen
    0.42
     montrer
    0.41
     MOQ
    0.41
     definir
    0.40
     venir
    0.39
     arrivée
    0.38
    Schmidt
    0.38
     வில
    0.38
    ヴィ
    0.38
    POSITIVE LOGITS
    Oops
    0.69
     Oops
    0.64
     inadvert
    0.57
     apologies
    0.57
     inadvertently
    0.56
     oops
    0.55
    sorry
    0.55
     accidentally
    0.54
     Sorry
    0.52
    Sorry
    0.52
    Act Density 0.001%

    No Known Activations