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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash

    This neuron activates on the term “adiabatic” (and its sub‐token segments), i.e. it flags occurrences of the word “adiabatic” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    scientific terms related to quantum mechanics and optimization processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     polar
    -0.07
     خارجی
    -0.07
     signatures
    -0.06
     Crest
    -0.06
     흔
    -0.06
    陶
    -0.06
     Daly
    -0.06
    LIMIT
    -0.06
     бути
    -0.06
    uae
    -0.06
    POSITIVE LOGITS
    ;}↵
    0.06
     Industry
    0.06
    Commands
    0.06
    اءة
    0.06
    _reserved
    0.06
     sock
    0.06
    outlined
    0.06
     roadway
    0.06
    χία
    0.06
    (WIN
    0.06
    Act Density 0.001%

    No Known Activations