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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects HTML/XML tag syntax and markup tokens (e.g. `<`, `>`, tag names like `li`/`a`, attributes like `href`, and related punctuation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erialize
    -0.07
    ert
    -0.06
    (ra
    -0.06
     vertex
    -0.06
     conver
    -0.06
    -op
    -0.06
    剣
    -0.06
     Desert
    -0.06
     Jordan
    -0.06
     tertiary
    -0.06
    POSITIVE LOGITS
    ?>><?
    0.07
    patial
    0.07
    _DX
    0.06
     واقعی
    0.06
     přítom
    0.06
     گونه
    0.06
     PreparedStatement
    0.06
     nghĩa
    0.06
    رسی
    0.06
    HY
    0.06
    Act Density 0.001%

    No Known Activations