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

    Neuronpedia

    INDEX
    Explanations

    elements related to design, particularly in reference to clean lines and shapes

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

    shape contours lines edges curves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.58
     gynhyrchwyd
    -0.56
    ppuden
    -0.48
    EnableWeb
    -0.48
    migrationBuilder
    -0.48
    ReusableCell
    -0.48
    transQ
    -0.47
     <>",
    -0.47
     GenerationType
    -0.47
    WriteTagHelper
    -0.46
    POSITIVE LOGITS
     shapes
    0.57
     contours
    0.54
     shape
    0.52
    IntoConstraints
    0.50
     sleek
    0.49
     contour
    0.48
    curves
    0.48
     architectural
    0.47
    shapes
    0.47
     angles
    0.47
    Act Density 0.010%

    No Known Activations