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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’
    -0.56
    ,
    -0.55
    '
    -0.50
     notwithstanding
    -0.48
     have
    -0.46
     easily
    -0.44
    toHexString
    -0.44
     indeed
    -0.44
     ignoring
    -0.44
     Lég
    -0.43
    POSITIVE LOGITS
    TagMode
    0.94
     GenerationType
    0.91
     kasarigan
    0.78
    EDEFAULT
    0.77
    MigrationBuilder
    0.75
    InvalidProtocol
    0.73
    DotNetBar
    0.72
    EndGlobalSection
    0.68
     estekak
    0.68
     pinulongan
    0.68
    Act Density 0.001%

    No Known Activations