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

    Neuronpedia

    INDEX
    Explanations

    code blocks and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getNodeId
    0.39
    getRedTeam
    0.39
     createFile
    0.34
     UITableView
    0.34
    ProductId
    0.33
    getItemId
    0.33
    ItemId
    0.33
    getColumnIndex
    0.32
     determinación
    0.32
     UILabel
    0.32
    POSITIVE LOGITS
     _
    0.38
    icao
    0.36
     raw
    0.36
     e
    0.36
     r
    0.35
    raw
    0.34
     my
    0.34
     d
    0.33
    str
    0.33
     _)
    0.33
    Act Density 0.254%

    No Known Activations