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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to rotation and transformation

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

    rotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anſ
    -0.43
     Esper
    -0.42
    IUrlHelper
    -0.42
     Buda
    -0.41
    sApp
    -0.40
     Marquis
    -0.40
     Diſ
    -0.40
    AsUp
    -0.40
    StringCopy
    -0.40
     ZAP
    -0.39
    POSITIVE LOGITS
     rotation
    1.34
     rotate
    1.28
     rotación
    1.23
     rotates
    1.23
     Rotation
    1.23
     rotations
    1.21
     rotated
    1.19
     Rotating
    1.17
    Rotation
    1.16
     rotating
    1.16
    Act Density 0.035%

    No Known Activations