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

    Neuronpedia

    INDEX
    Explanations

    invariant

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the term “invariant” (and its morphological variants such as “variants” or “variance”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    身体
    -0.07
    Based
    -0.07
     ;;^
    -0.07
     tyto
    -0.06
    Sep
    -0.06
    pagination
    -0.06
    یس
    -0.06
    ですか
    -0.06
    )((((
    -0.06
    endcode
    -0.06
    POSITIVE LOGITS
     invariant
    0.14
    Invariant
    0.08
    .Invariant
    0.08
     İn
    0.08
     Hawai
    0.07
     disaster
    0.07
    variant
    0.07
     invent
    0.07
     DataContext
    0.07
    .InvariantCulture
    0.07
    Act Density 0.002%

    No Known Activations