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

    Neuronpedia

    INDEX
    Explanations

    responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liquid
    -0.07
    _url
    -0.07
     scraping
    -0.06
     entertaining
    -0.06
    typing
    -0.06
     archives
    -0.06
    یس
    -0.06
     headphone
    -0.06
     PM
    -0.06
    (mock
    -0.06
    POSITIVE LOGITS
     donating
    0.07
    Pooling
    0.06
     mutually
    0.06
    (ball
    0.06
    ล
    0.06
     CEL
    0.06
     एल
    0.06
    ιώ
    0.06
     flattering
    0.06
    ้อง
    0.06
    Act Density 0.313%

    No Known Activations