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

    Neuronpedia

    INDEX
    Explanations

    quaternions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Economic
    -0.10
    催
    -0.10
    Revenue
    -0.09
     admissions
    -0.09
     Admissions
    -0.09
     terrace
    -0.09
     subsidy
    -0.09
    Tier
    -0.09
    Referral
    -0.09
    College
    -0.09
    POSITIVE LOGITS
     quaternion
    0.19
     Quaternion
    0.16
    Quaternion
    0.15
     quat
    0.13
    Quat
    0.12
     rotations
    0.11
    quat
    0.11
    rotation
    0.10
     Rotation
    0.10
     вращ
    0.10
    Act Density 0.006%

    No Known Activations