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

    Neuronpedia

    INDEX
    Explanations

    walls and surfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    話を
    0.47
     anonym
    0.44
     엄청
    0.44
     hypnosis
    0.43
     disinformation
    0.43
    匿名
    0.43
     психо
    0.42
     LocalDate
    0.42
     পাগল
    0.41
     gubernatorial
    0.41
    POSITIVE LOGITS
     surfaces
    0.74
    墙
    0.70
     wall
    0.66
    ผน
    0.66
     walls
    0.63
     ceilings
    0.63
    wall
    0.61
     indoors
    0.61
     दीवार
    0.61
     superficies
    0.61
    Act Density 0.021%

    No Known Activations