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

    Neuronpedia

    INDEX
    Explanations

    references to physical walls and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    wall in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rücks
    -0.33
     vloer
    -0.33
     tents
    -0.33
    KHR
    -0.30
     campsites
    -0.30
    lwjgl
    -0.30
     Stakes
    -0.30
    хь
    -0.29
    legte
    -0.29
    legt
    -0.28
    POSITIVE LOGITS
     wall
    0.93
    wall
    0.77
     parede
    0.76
    Wall
    0.70
     Wall
    0.69
     parete
    0.69
    WALL
    0.69
     WALL
    0.68
     dinding
    0.63
    墙
    0.63
    Act Density 0.011%

    No Known Activations