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

    Neuronpedia

    INDEX
    Explanations

    concepts related to physics and mathematics, particularly those associated with structures and measurements

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

    Mentions "radius", "circular", or "diameter"

    np_acts-logits-general · gemini-2.0-flash

    radius long

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stair
    -0.45
     iceberg
    -0.43
    弄
    -0.43
     Stair
    -0.40
     slat
    -0.40
     Block
    -0.40
     Brock
    -0.39
     Barak
    -0.39
    stairs
    -0.39
     Labor
    -0.39
    POSITIVE LOGITS
     radius
    1.60
    radius
    1.40
     Radius
    1.38
     radii
    1.36
     diameter
    1.32
    Radius
    1.32
     Diameter
    1.23
     concentric
    1.18
    diameter
    1.17
     circle
    1.16
    Act Density 0.513%

    No Known Activations