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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Layout
    -0.07
     مشاركة
    -0.07
     clearTimeout
    -0.06
     UITableViewCell
    -0.06
    ListItemText
    -0.06
    ursive
    -0.06
    IMPORTANT
    -0.06
    Metadata
    -0.06
    burgh
    -0.06
     Powder
    -0.06
    POSITIVE LOGITS
    (global
    0.08
     olası
    0.07
    ulkan
    0.06
    ivial
    0.06
    )>>
    0.06
    .""
    0.06
    -stack
    0.06
     seems
    0.06
    ，這
    0.06
     Αλ
    0.06
    Act Density 0.001%

    No Known Activations