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

    Neuronpedia

    INDEX
    Explanations

    structure and formatting related to data types and object definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code syntax and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.79
    -0.73
    <unused41>
    -0.71
    <unused14>
    -0.71
    RegressionTest
    -0.71
    <unused43>
    -0.71
    transQ
    -0.71
    <unused79>
    -0.71
    <unused16>
    -0.71
    <unused28>
    -0.71
    POSITIVE LOGITS
    　
    0.31
    《
    0.30
    JsonPropertyName
    0.29
    viewType
    0.29
     single
    0.26
    ViewType
    0.26
    $_['
    0.25
    ViewImports
    0.23
     《
    0.22
     la
    0.22
    Act Density 0.007%

    No Known Activations