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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash

    metadata and information about software packages in a structured format.

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

    This neuron detects the occurrence of the term “readme” (e.g. in “# read me” headings or README fields).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     多
    -0.07
    owl
    -0.07
    ournament
    -0.07
    .oracle
    -0.06
    Toggle
    -0.06
    .link
    -0.06
     bour
    -0.06
     Gods
    -0.06
    opup
    -0.06
     وذلك
    -0.06
    POSITIVE LOGITS
    尽管
    0.07
     INCLUDING
    0.06
     represent
    0.06
     Iraq
    0.06
    感觉
    0.06
    Iran
    0.06
     overdose
    0.06
     Authorization
    0.06
    ρθ
    0.06
     harmon
    0.06
    Act Density 0.000%

    No Known Activations