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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the word “command” (including as part of compound identifiers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     playoffs
    -0.07
     )↵
    -0.07
    -round
    -0.07
     embraced
    -0.07
    /'.$
    -0.07
     drilling
    -0.07
    Post
    -0.07
    -ahead
    -0.07
     respective
    -0.06
     second
    -0.06
    POSITIVE LOGITS
     उन
    0.06
    _mono
    0.06
     แล
    0.06
     Boo
    0.06
    екти
    0.06
    شن
    0.06
     اب
    0.06
     Alman
    0.06
    /support
    0.06
    (GL
    0.06
    Act Density 0.048%

    No Known Activations