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

    Neuronpedia

    INDEX
    Explanations

    references to tiles and related terminology

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

    tile or tilde

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.51
     محفوظة
    -0.45
     Autorisations
    -0.44
    cstdio
    -0.44
    جغرافيا
    -0.44
     Freedman
    -0.42
    xions
    -0.42
    AllowUser
    -0.42
    return
    -0.41
     Goodman
    -0.41
    POSITIVE LOGITS
     Tile
    1.30
     tile
    1.25
     TILE
    1.23
    Tile
    1.19
     tiles
    1.15
     Tiles
    1.09
    tile
    0.98
    Tiles
    0.97
    TILE
    0.90
    tiles
    0.84
    Act Density 0.016%

    No Known Activations