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

    Neuronpedia

    INDEX
    Explanations

    Reflections and paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sponsoring
    -0.09
     sponsorship
    -0.08
     arts
    -0.08
    =set
    -0.08
     proclaim
    -0.08
     Promise
    -0.07
     necessities
    -0.07
     emphasis
    -0.07
     Sup
    -0.07
    Exe
    -0.07
    POSITIVE LOGITS
     intercambio
    0.09
     tiled
    0.09
     huizen
    0.09
     Compart
    0.09
     Exchanges
    0.09
     expansions
    0.09
     espejo
    0.09
     expansión
    0.09
     billi
    0.09
    Tiles
    0.09
    Act Density 0.006%

    No Known Activations