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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects HTML ordered‐list markup (e.g. the `<ol start="…">` tags and related tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     todas
    -0.07
    ête
    -0.06
    /graph
    -0.06
     Aydın
    -0.06
    .factory
    -0.06
    Ohio
    -0.06
    ोध
    -0.06
    ～
    -0.06
    __.__
    -0.06
     honey
    -0.06
    POSITIVE LOGITS
     regenerated
    0.07
    oxic
    0.06
     skup
    0.06
     Revised
    0.06
     Rosie
    0.06
    國家
    0.06
     inexperienced
    0.06
    uring
    0.06
    vised
    0.06
    ร
    0.06
    Act Density 0.001%

    No Known Activations