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

    Neuronpedia

    INDEX
    Explanations

    16

    np_max-act · gemini-2.0-flash

    The neuron detects timestamp fields (numeric date/time strings with colons, periods, and timezone offsets) in the blog comment metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     groin
    -0.07
     feet
    -0.07
     top
    -0.07
    Pal
    -0.07
     far
    -0.07
    水
    -0.07
     Clip
    -0.07
     gid
    -0.06
     Hin
    -0.06
    ’all
    -0.06
    POSITIVE LOGITS
     rộng
    0.06
     солн
    0.06
    tensorflow
    0.06
     temas
    0.06
     жив
    0.06
     воно
    0.06
    (Cell
    0.06
     باشید
    0.06
    .lineTo
    0.06
    	MPI
    0.06
    Act Density 0.004%

    No Known Activations