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

    Neuronpedia

    INDEX
    Explanations

    formulas/expressions

    np_max-act · gemini-2.0-flash

    mathematical formulations and concepts related to quantum mechanics and dynamical systems.

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

    This neuron detects references to precise mathematical or technical expressions—terms like “exact,” “integral,” “formulas,” “expressions,” and other jargon signaling formal quantitative results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     homework
    -0.06
    roscope
    -0.06
     safe
    -0.06
    .timestamp
    -0.06
    ψει
    -0.06
     tents
    -0.06
    note
    -0.06
    .Get
    -0.06
    rar
    -0.06
    .jpeg
    -0.06
    POSITIVE LOGITS
    .ComponentPlacement
    0.07
     актив
    0.07
     Prague
    0.06
    .SpringApplication
    0.06
    นาม
    0.06
     peu
    0.06
    北市
    0.06
    HTTPRequest
    0.06
    owards
    0.06
     tekst
    0.06
    Act Density 0.018%

    No Known Activations