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

    Neuronpedia

    INDEX
    Explanations

    warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warning
    -0.81
     Warning
    -0.69
    ScopeManager
    -0.69
    NavController
    -0.65
    WebServlet
    -0.62
     warnings
    -0.61
     WARNING
    -0.61
     autorytatywna
    -0.60
     BrowserModule
    -0.59
     Warnings
    -0.58
    POSITIVE LOGITS
     bells
    0.57
     bell
    0.51
     CascadeType
    0.48
    INDICATOR
    0.47
     civili
    0.47
     cytok
    0.47
    requestCode
    0.45
    queryInterface
    0.45
    clearance
    0.44
    getDeclared
    0.44
    Act Density 0.004%

    No Known Activations