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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects snake_case identifiers (e.g. column names containing an underscore).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exchanged
    -0.07
    _memcpy
    -0.06
    ування
    -0.06
    .footer
    -0.06
    _Report
    -0.06
     Exchange
    -0.06
     Fritz
    -0.06
    -three
    -0.06
     enth
    -0.06
    平方
    -0.06
    POSITIVE LOGITS
    DATE
    0.07
     Smithsonian
    0.07
     ℝ
    0.07
     mutually
    0.06
     CODE
    0.06
     mListener
    0.06
    (def
    0.06
    eq
    0.06
    宫
    0.06
    �
    0.06
    Act Density 0.217%

    No Known Activations