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

    Neuronpedia

    INDEX
    Explanations

    structured

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “structured” (especially within the word “unstructured”), i.e. it detects mentions of unstructured or structured data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     домаш
    -0.07
     corrupt
    -0.06
     항
    -0.06
     salt
    -0.06
     Night
    -0.06
    ubbo
    -0.06
    人
    -0.06
     mans
    -0.06
    apper
    -0.06
     nause
    -0.06
    POSITIVE LOGITS
     Spir
    0.07
    spacing
    0.07
     रक
    0.07
      ↵↵
    0.06
     Interr
    0.06
     😉↵↵
    0.06
    سون
    0.06
    ='')↵
    0.06
     DISPATCH
    0.06
     فر
    0.06
    Act Density 0.007%

    No Known Activations