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

    Neuronpedia

    INDEX
    Explanations

    Sorting algorithms

    np_max-act · gemini-2.0-flash

    This neuron detects the special header‐delimiter token (“<|start_header_id|>”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    еление
    -0.07
     UIStoryboard
    -0.07
    _d
    -0.06
    uting
    -0.06
     mitochondrial
    -0.06
     fined
    -0.06
    lemen
    -0.06
    edy
    -0.06
    -0.06
     util
    -0.06
    POSITIVE LOGITS
     πρώτη
    0.07
     παρα
    0.06
    _so
    0.06
    GetProcAddress
    0.06
    /menu
    0.06
     sana
    0.06
     نادي
    0.06
    Senior
    0.06
     －
    0.06
     formidable
    0.06
    Act Density 0.015%

    No Known Activations