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

    Neuronpedia

    INDEX
    Explanations

    door opening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pprint
    0.45
    残酷
    0.41
     pollution
    0.40
     totam
    0.39
     persec
    0.38
     synt
    0.38
     pará
    0.38
     cytos
    0.38
     ascor
    0.38
     enne
    0.38
    POSITIVE LOGITS
     door
    2.42
     doors
    2.38
     двери
    2.16
    Door
    2.13
     Door
    2.08
     дверь
    2.08
    door
    2.05
    Doors
    2.02
    门
    2.02
     Doors
    1.97
    Act Density 0.047%

    No Known Activations