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

    Neuronpedia

    INDEX
    Explanations

    +- and *- symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +-
    -0.92
    +-
    -0.78
     Hote
    -0.70
    °-
    -0.68
     expectancy
    -0.59
     cer
    -0.55
     hote
    -0.55
    -
    -0.52
    KeyValuePair
    -0.52
     consta
    -0.51
    POSITIVE LOGITS
    fromnode
    0.73
    Биография
    0.62
    parsedMessage
    0.59
     AssemblyTitle
    0.58
    
    0.58
     AssemblyCulture
    0.56
    SourceChecksum
    0.54
    posedge
    0.54
     HttpNotFound
    0.54
    0.51
    Act Density 0.069%

    No Known Activations