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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     an
    -0.54
     a
    -0.53
     the
    -0.42
     names
    -0.42
     naming
    -0.39
     its
    -0.39
     nearby
    -0.38
     more
    -0.38
     in
    -0.37
     legal
    -0.37
    POSITIVE LOGITS
    TagMode
    1.02
    AddTagHelper
    0.98
    Билгалдахарш
    0.96
    SourceChecksum
    0.93
     Roskov
    0.84
     ostavi
    0.83
    expandindo
    0.83
     متعلقه
    0.81
     propOrder
    0.81
     AssemblyTitle
    0.81
    Act Density 0.091%

    No Known Activations