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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on the opening “This …” or “A …” sentence of a Javadoc/comment summary (e.g. “This class…,” “This is…,” “A class to…,” etc.)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ramos
    -0.07
    _SERVICE
    -0.07
     Dough
    -0.07
    uate
    -0.06
     vtx
    -0.06
     awkward
    -0.06
    SSION
    -0.06
     ECC
    -0.06
     crosses
    -0.06
    BYTES
    -0.06
    POSITIVE LOGITS
    (bind
    0.07
    렵
    0.06
     última
    0.06
    لكتر
    0.06
    pipe
    0.06
     concentr
    0.06
     技
    0.06
     полити
    0.06
     indispens
    0.06
    να
    0.06
    Act Density 0.012%

    No Known Activations