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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    code snippets related to data manipulation in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects Markdown‐style fenced code blocks, i.e. the triple‐backtick delimiters that mark code examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ไฟ
    -0.07
     VA
    -0.07
     woods
    -0.07
     цін
    -0.06
     ego
    -0.06
    EFR
    -0.06
     Bones
    -0.06
    番号
    -0.06
     Busty
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Existing
    0.07
    кое
    0.06
    acies
    0.06
    Existing
    0.06
     Functions
    0.06
    lat
    0.06
    *y
    0.06
     Blogs
    0.06
    sortBy
    0.06
    SOEVER
    0.06
    Act Density 0.065%

    No Known Activations