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

    Neuronpedia

    INDEX
    Explanations

    emission

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect domain‐specific scientific terminology—especially technical astrophysics words describing emission processes and measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rij
    -0.07
     balcony
    -0.07
     foreclosure
    -0.07
    сен
    -0.07
     increment
    -0.07
    (box
    -0.06
     LIST
    -0.06
     paintings
    -0.06
    (symbol
    -0.06
    study
    -0.06
    POSITIVE LOGITS
     concurrency
    0.07
     peripherals
    0.06
    ResponseStatus
    0.06
    equalsIgnoreCase
    0.06
    whether
    0.06
     Boiler
    0.06
    .HttpSession
    0.06
    Adventure
    0.06
    _]
    0.06
    汉
    0.06
    Act Density 0.010%

    No Known Activations