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

    Neuronpedia

    INDEX
    Explanations

    terms related to angles and rotations in a physical or mathematical context

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

    angle, orientation, steering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.81
    ConstraintMaker
    -0.78
    ThroughAttribute
    -0.77
     utafitiHapana
    -0.71
    <unused14>
    -0.69
    <unused23>
    -0.68
    <unused28>
    -0.68
    <unused3>
    -0.68
    <unused16>
    -0.68
    <unused41>
    -0.68
    POSITIVE LOGITS
    styleUrls
    0.32
     cab
    0.30
    <eos>
    0.30
    蜒
    0.30
    steering
    0.30
     moment
    0.29
     ده
    0.29
     dü
    0.29
    ‌پ
    0.28
     مص
    0.28
    Act Density 0.009%

    No Known Activations