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

    Neuronpedia

    INDEX
    Explanations

    technology and technical topics

    np_max-act · gemini-2.0-flash

    The neuron fires on short uppercase or mixed‐case tokens that name programming languages, file‐I/O modes, or markup formats (e.g. “Java”, “rb”, “HTML”, “XHTML”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pairing
    -0.07
     configured
    -0.07
     nid
    -0.06
    .RowStyles
    -0.06
     Needs
    -0.06
    δια
    -0.06
    ौर
    -0.06
    ptime
    -0.06
    alamat
    -0.06
    LABEL
    -0.06
    POSITIVE LOGITS
    ělí
    0.07
     голос
    0.06
     німець
    0.06
    _()↵
    0.06
     IPv
    0.06
    -В
    0.06
    _:*
    0.06
    (A
    0.06
    □
    0.06
    CompatActivity
    0.06
    Act Density 0.081%

    No Known Activations