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

    Neuronpedia

    INDEX
    Explanations

    diagnostics and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guard
    -0.96
     Guard
    -0.85
     broad
    -0.85
     Broad
    -0.83
    guard
    -0.81
    Guard
    -0.77
    Broad
    -0.75
    broad
    -0.75
     GUARD
    -0.73
    BROAD
    -0.62
    POSITIVE LOGITS
    Personensuche
    0.76
    PerformLayout
    0.69
    CloseOperation
    0.68
     Réponses
    0.68
    BASEPATH
    0.66
    UserScript
    0.65
    例句
    0.65
     onPostExecute
    0.60
    Portail
    0.60
    migrationBuilder
    0.60
    Act Density 0.191%

    No Known Activations