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

    Neuronpedia

    INDEX
    Explanations

    numeric values and file-related terms

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

    Code diff markers (+, -, @@)

    np_acts-logits-general · gemini-2.0-flash

    git commit diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.81
     defaultstate
    -0.67
    UnsafeEnabled
    -0.64
    Архівовано
    -0.64
    XmlAccessType
    -0.63
    migrationBuilder
    -0.62
     noqa
    -0.61
    ,:),
    -0.59
    ﹍﹍﹍
    -0.59
    越多
    -0.56
    POSITIVE LOGITS
     IBOutlet
    0.48
    arusian
    0.47
    ohist
    0.46
    wußt
    0.46
     افتراض
    0.46
    IonicModule
    0.46
     يتيمه
    0.46
    istan
    0.45
    TypedDataSet
    0.45
     onView
    0.44
    Act Density 0.419%

    No Known Activations