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

    Neuronpedia

    INDEX
    Explanations

    code related to data serialization with a focus on packed fields and visitor patterns

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.57
    amil
    -0.51
    område
    -0.51
     V
    -0.49
    wicz
    -0.49
     e
    -0.49
    iense
    -0.49
     
    -0.49
    <strong>
    -0.48
     E
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    1.20
    SharedDtor
    1.16
    ValueStyle
    1.16
    parsedMessage
    1.14
    MigrationBuilder
    1.14
     BoxFit
    1.13
    styleType
    1.10
     EClass
    1.09
    endphp
    1.09
     ModelExpression
    1.09
    Act Density 2.501%

    No Known Activations