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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BlackBerry
    -0.07
    _season
    -0.07
     وسی
    -0.06
    											↵
    -0.06
     Provid
    -0.06
    IDGET
    -0.06
    Barcode
    -0.06
    lerdir
    -0.06
    /articles
    -0.06
     lyr
    -0.06
    POSITIVE LOGITS
     kingdom
    0.08
    .nil
    0.07
     edip
    0.06
     yerine
    0.06
     factors
    0.06
     prefixed
    0.06
     diệt
    0.06
     recording
    0.06
     *)
    0.06
     regularization
    0.06
    Act Density 0.009%

    No Known Activations