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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron fires on XML attribute names that use a namespace prefix (e.g. “app:…”, “tools:…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     вд
    -0.07
    arsimp
    -0.07
    енную
    -0.07
    -е
    -0.07
    *)↵↵
    -0.06
    Execution
    -0.06
    DBNull
    -0.06
    $fdata
    -0.06
    适
    -0.06
     ků
    -0.06
    POSITIVE LOGITS
    ování
    0.06
    (nome
    0.06
    UNE
    0.06
    atalog
    0.06
    ารถ
    0.06
    .argv
    0.06
    exion
    0.06
     purge
    0.06
    bah
    0.06
    ηση
    0.06
    Act Density 0.001%

    No Known Activations