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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     difference
    -1.01
     Difference
    -0.98
    difference
    -0.98
    Difference
    -0.94
     Differences
    -0.85
     DIFFERENCE
    -0.80
     Differential
    -0.75
    Differences
    -0.74
     differences
    -0.72
    differences
    -0.71
    POSITIVE LOGITS
    MigrationBuilder
    0.56
     EconPapers
    0.48
     defaultstate
    0.48
    Демографія
    0.47
     plonge
    0.47
    WithIOException
    0.45
    Indented
    0.45
     Kirche
    0.42
    حياته
    0.41
     propOrder
    0.40
    Act Density 0.041%

    No Known Activations