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

    Neuronpedia

    INDEX
    Explanations

    a mix of mathematical terms and errors related to extracting text from diagrams

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stops
    -0.62
     Mahomet
    -0.60
     Stops
    -0.59
    ंदीखरीदारी
    -0.58
    seamnă
    -0.56
     dagegen
    -0.56
     magasiner
    -0.56
     Comercial
    -0.55
    SourceChecksum
    -0.55
    cestershire
    -0.55
    POSITIVE LOGITS
    Portály
    0.54
     المعيارى
    0.53
    DebuggerNonUser
    0.52
     SwiftUI
    0.52
    HasForeignKey
    0.52
    WebElement
    0.51
    ISupport
    0.50
    <bos>
    0.48
    noStroke
    0.48
    ModelAttribute
    0.48
    Act Density 4.550%

    No Known Activations