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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the ImageIO library (the “image” + “io” tokens) in code examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    individual
    -0.07
    SetName
    -0.07
     breath
    -0.07
     interrupted
    -0.06
     Ngoài
    -0.06
    .score
    -0.06
    ��
    -0.06
     libros
    -0.06
    今
    -0.06
    _CURRENT
    -0.06
    POSITIVE LOGITS
    HF
    0.06
    $pdf
    0.06
     jenter
    0.06
     TextArea
    0.06
    管理员
    0.06
     숙
    0.06
    ��이지
    0.06
    (fd
    0.06
     RCMP
    0.06
     postcode
    0.06
    Act Density 0.021%

    No Known Activations