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

    Neuronpedia

    INDEX
    Explanations

    perspective

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens and numeric/measurement-related elements (numbers, dates, percentages, units).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    _WIFI
    -0.07
    .print
    -0.07
     vscode
    -0.06
     sane
    -0.06
    ******/
    -0.06
    WINDOWS
    -0.06
     اخ
    -0.06
    riteln
    -0.06
     Tyr
    -0.06
     startups
    -0.06
    POSITIVE LOGITS
     můž
    0.06
    �
    0.06
    的な
    0.06
    truck
    0.06
    ubbo
    0.06
     complications
    0.06
     Chic
    0.06
    柜
    0.06
    _WRONG
    0.06
    registr
    0.06
    Act Density 13.323%

    No Known Activations