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

    Neuronpedia

    INDEX
    Explanations

    dx

    np_max-act · gemini-2.0-flash

    discussions related to mathematical integration techniques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the differential element tokens (like “dx”, “dθ”, “du”, etc.) in integral expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .FLOAT
    -0.07
    .nano
    -0.06
     A
    -0.06
    eket
    -0.06
     volley
    -0.06
     Four
    -0.06
    ieran
    -0.05
    role
    -0.05
     axis
    -0.05
    ющихся
    -0.05
    POSITIVE LOGITS
     Simpl
    0.08
    _CONSTANT
    0.08
    _gl
    0.07
     завод
    0.06
    thren
    0.06
    "He
    0.06
    -dr
    0.06
    _hello
    0.06
    <main
    0.06
     جی
    0.06
    Act Density 0.004%

    No Known Activations