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

    Neuronpedia

    INDEX
    Explanations

    references to lattice structures in mathematical or physical contexts

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

    lattice structures and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.51
    tagext
    -0.45
     guan
    -0.44
    保
    -0.43
    endfor
    -0.42
     BPA
    -0.41
    Liam
    -0.41
    Superman
    -0.40
    請繼續往下閱讀
    -0.40
     Chopra
    -0.40
    POSITIVE LOGITS
     lattice
    2.17
     Lattice
    1.98
    Lattice
    1.89
    lattice
    1.79
     lattices
    1.48
     решет
    0.89
    格子
    0.84
     grid
    0.73
     trellis
    0.72
     réseaux
    0.70
    Act Density 0.010%

    No Known Activations