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

    Neuronpedia

    INDEX
    Explanations

    L

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific resource or content formats (e.g. “pdfs,” “brochures,” “videos,” “via WhatsApp”) when suggesting materials to provide.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Films
    -0.07
     dumping
    -0.06
     Dawn
    -0.06
    -news
    -0.06
    Encoded
    -0.06
    傳
    -0.06
     schwar
    -0.06
    _mass
    -0.06
     Assault
    -0.06
     explosive
    -0.06
    POSITIVE LOGITS
     ("-
    0.07
    Arrays
    0.06
     contentValues
    0.06
     Nhưng
    0.06
     jQuery
    0.06
     Bentley
    0.06
     grap
    0.06
    .Contains
    0.06
     Ж
    0.06
    ObjectId
    0.06
    Act Density 0.594%

    No Known Activations