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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of regular‐expression search and matching constructs (e.g. NSRegularExpression options and related method calls) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ⟩
    -0.07
     PR
    -0.06
     panicked
    -0.06
     巴
    -0.06
     真
    -0.06
     IGN
    -0.06
    rts
    -0.06
    _cast
    -0.06
    .vol
    -0.06
    aepernick
    -0.06
    POSITIVE LOGITS
    -between
    0.07
    0.07
     resources
    0.07
     Superintendent
    0.06
     inspector
    0.06
    一年
    0.06
     Hunter
    0.06
    .Library
    0.06
     Shay
    0.06
     Inspector
    0.06
    Act Density 0.116%

    No Known Activations