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

    Neuronpedia

    INDEX
    Explanations

    references to walls and their characteristics in various contexts

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

    "wall" or "walls"

    np_acts-logits-general · gemini-2.0-flash

    wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.47
    ?}",
    -0.45
    chaun
    -0.44
    濁
    -0.44
    strptime
    -0.43
     autorytatywna
    -0.42
    emlrt
    -0.40
    NewUrlParser
    -0.40
     sī
    -0.40
    prefixer
    -0.40
    POSITIVE LOGITS
     wall
    1.27
     walls
    1.21
    Wall
    1.15
     WALL
    1.15
     Wall
    1.13
    Walls
    1.09
     Walls
    1.09
    wall
    1.03
    walls
    0.99
     paredes
    0.95
    Act Density 0.103%

    No Known Activations