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

    Neuronpedia

    INDEX
    Explanations

    terms related to design elements and aesthetics

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

    visual outlines and shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.69
     MainAxisSize
    -0.64
    клопе
    -0.64
     nahilalakip
    -0.63
     <=",
    -0.62
    transQ
    -0.61
    rrggbb
    -0.61
    nologue
    -0.60
    adpleegd
    -0.60
    invokeLater
    -0.58
    POSITIVE LOGITS
     lines
    0.57
     contours
    0.54
    线条
    0.51
     trekken
    0.50
     shape
    0.47
     outlines
    0.47
     líneas
    0.46
     contour
    0.46
     shapes
    0.46
     Linien
    0.45
    Act Density 0.025%

    No Known Activations