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

    Neuronpedia

    INDEX
    Explanations

    connecting/attaching

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on “-ing” words—especially gerund or present‐participle action terms (e.g. curing, joining, snapping, fastening) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bác
    -0.08
     

↵
    -0.07
     isi
    -0.07
    ايل
    -0.06
    orama
    -0.06
     کری
    -0.06
    .PLL
    -0.06
     객체
    -0.06
    رانی
    -0.06
    animated
    -0.06
    POSITIVE LOGITS
    Dimension
    0.07
     acted
    0.06
     fraternity
    0.06
    üş
    0.06
     telefono
    0.06
     Tories
    0.06
    -O
    0.06
     beauty
    0.06
    /back
    0.06
     StatefulWidget
    0.06
    Act Density 0.131%

    No Known Activations