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

    Neuronpedia

    INDEX
    Explanations

    terms related to canonical transformations in mathematical or theoretical physics contexts

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

    canonical transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.43
     FormsModule
    -0.42
    stddef
    -0.41
    <bos>
    -0.40
    ↵↵↵↵
    -0.37
     ض
    -0.37
    Dmit
    -0.37
    зд
    -0.36
    setList
    -0.36
    Burt
    -0.36
    POSITIVE LOGITS
    Canonical
    2.39
    canonical
    2.39
     canonical
    2.38
     Canonical
    2.36
    canon
    1.20
     canon
    1.20
    Canon
    1.12
     Canon
    1.12
     cannon
    0.92
     canons
    0.91
    Act Density 0.009%

    No Known Activations