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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to geometry and polygon classification

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

    Geometric entities and polygon properties

    np_acts-logits-general · gemini-2.0-flash

    lines and geometric shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.64
     uska
    -0.57
    parsedMessage
    -0.57
    ReusableCell
    -0.56
     Banda
    -0.55
    chium
    -0.52
     ControllerBase
    -0.52
     Mounts
    -0.52
     carousel
    -0.52
    synchron
    -0.50
    POSITIVE LOGITS
     points
    0.77
     polygon
    0.72
     line
    0.68
    points
    0.66
    etragen
    0.66
     vertices
    0.65
     geometry
    0.65
     point
    0.65
     Points
    0.64
    Polyline
    0.63
    Act Density 0.805%

    No Known Activations