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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash

    The neuron fires on the vertical-bar separators used in table-like structures (e.g. Markdown-style column delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _profile
    -0.07
    .bumptech
    -0.06
    SECTION
    -0.06
    (images
    -0.06
    )view
    -0.06
    ƒ
    -0.06
     براى
    -0.06
     unidad
    -0.06
     memories
    -0.06
     BUFFER
    -0.06
    POSITIVE LOGITS
     coch
    0.07
    ãi
    0.07
     |↵
    0.06
     Greenwich
    0.06
     internally
    0.06
    +/
    0.06
     cha
    0.06
    đ
    0.06
    	Query
    0.06
    _cate
    0.06
    Act Density 0.004%

    No Known Activations