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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash

    This neuron detects markup tags (e.g. HTML/XML tags enclosed in “<” and “>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _exit
    -0.07
    ()['
    -0.07
    Exit
    -0.07
    .long
    -0.06
     Shrine
    -0.06
    Router
    -0.06
     visited
    -0.06
    cmp
    -0.06
     Satellite
    -0.06
    ίο
    -0.06
    POSITIVE LOGITS
     flavorful
    0.06
     вспом
    0.06
     chăm
    0.06
    createForm
    0.06
    üslüman
    0.06
    hetic
    0.06
     OA
    0.06
     podmínky
    0.06
     внут
    0.06
    SEMB
    0.06
    Act Density 0.011%

    No Known Activations