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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash

    scientific terms related to genetics and molecular biology.

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

    This neuron detects the typical scientific-paper result‐statement phrase “Here we …” (e.g. “Here we show/describe/review/have examined …”) that introduces the authors’ main findings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    adu
    -0.07
     alarmed
    -0.07
    Elite
    -0.07
    PTS
    -0.06
    ynet
    -0.06
    -function
    -0.06
    _MIDDLE
    -0.06
     dokonce
    -0.06
     Alpine
    -0.06
     hver
    -0.06
    POSITIVE LOGITS
     biom
    0.07
    ');↵↵
    0.06
     उच
    0.06
     IOC
    0.06
    (IServiceCollection
    0.06
     nói
    0.06
     GObject
    0.06
    *);↵↵
    0.06
    qrstuvwxyz
    0.06
     io
    0.06
    Act Density 0.045%

    No Known Activations