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

    Neuronpedia

    INDEX
    Explanations

    door and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вр
    0.37
     numerator
    0.37
     graph
    0.36
    េរ
    0.36
     orbit
    0.35
     pollution
    0.35
     openly
    0.35
    ジナル
    0.35
     circon
    0.35
     intercept
    0.34
    POSITIVE LOGITS
     door
    4.31
     doors
    4.03
    Door
    3.81
     Door
    3.80
    door
    3.75
     двери
    3.58
    门
    3.50
     дверь
    3.45
    Doors
    3.44
     DOOR
    3.41
    Act Density 0.063%

    No Known Activations