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

    Neuronpedia

    INDEX
    Explanations

    references to blame or dishonesty associated with various individuals and groups

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

    Political commentary/discussion

    np_acts-logits-general · gemini-2.0-flash

    political criticism of politicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.15
    ViewFeatures
    -0.99
    OGND
    -0.98
     AssemblyCulture
    -0.97
    AccessorTable
    -0.96
     ExecuteAsync
    -0.92
    MLLoader
    -0.92
    ngdoc
    -0.90
    RectangleBorder
    -0.87
    DockStyle
    -0.87
    POSITIVE LOGITS
     hypocrisy
    0.77
     political
    0.76
     Political
    0.69
     politicians
    0.68
     POLITICAL
    0.66
     hypocritical
    0.66
     politico
    0.64
     news
    0.62
     laughable
    0.59
     politici
    0.59
    Act Density 0.770%

    No Known Activations