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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash

    mathematical expressions relating to derivatives and differentiation techniques.

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

    This neuron activates on mentions of taking derivatives—especially the “d/dx” or “dx” notation and references to using product‐ and chain‐rule steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    conversion
    -0.07
    -med
    -0.06
    "io
    -0.06
    uations
    -0.06
    ioc
    -0.06
    .recyclerview
    -0.06
     Ide
    -0.06
    andalone
    -0.06
    nable
    -0.06
     Satellite
    -0.06
    POSITIVE LOGITS
     enforcing
    0.07
    _unicode
    0.07
    .bpm
    0.06
     LEG
    0.06
     věci
    0.06
    ULE
    0.06
     DEL
    0.06
     chóng
    0.06
     труб
    0.06
    ToLower
    0.06
    Act Density 0.013%

    No Known Activations