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

    Neuronpedia

    INDEX
    Explanations

    Germanwings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laden
    1.02
     whipped
    0.94
     evocative
    0.92
     plough
    0.91
     plowed
    0.91
     reinforced
    0.91
     whistling
    0.90
     anthrop
    0.88
     braided
    0.88
     bolstered
    0.87
    POSITIVE LOGITS
    System
    0.83
    Math
    0.81
    Usuario
    0.79
    <unused60>
    0.76
    String
    0.76
    Parser
    0.76
    Aluno
    0.75
    获取
    0.75
    Mode
    0.75
    为
    0.74
    Act Density 0.000%

    No Known Activations