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

    Neuronpedia

    INDEX
    Explanations

    rotate

    np_max-act · gemini-2.0-flash

    functions that create transformation matrices from quaternion representations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on terms describing geometric transformation operations—especially rotations (e.g. “rotate,” “rotation,” rotation matrices) in 3D graphics contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _intersect
    -0.07
    $insert
    -0.07
     consulting
    -0.07
    .ta
    -0.06
    ifestyle
    -0.06
     ramen
    -0.06
     SEL
    -0.06
     últ
    -0.06
     Ada
    -0.06
    She
    -0.06
    POSITIVE LOGITS
    Tutorial
    0.07
    ового
    0.07
    Automation
    0.06
    Enemies
    0.06
    ών
    0.06
    leased
    0.06
    asury
    0.06
     sands
    0.06
     �
    0.06
    scope
    0.06
    Act Density 0.007%

    No Known Activations