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

    Neuronpedia

    INDEX
    Explanations

    density measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     эмоциона
    0.52
     क्रेडिट
    0.50
    监听页面
    0.47
    选举
    0.47
    EventEmitter
    0.47
    multiSelectList
    0.46
    Emojis
    0.45
    ApiCalls
    0.44
     entretenimiento
    0.44
     ಚುನ
    0.44
    POSITIVE LOGITS
     density
    2.27
    Density
    2.09
     Density
    2.02
    density
    2.00
     densities
    1.93
    密度
    1.93
     densidad
    1.76
     denser
    1.67
     densité
    1.65
     dense
    1.57
    Act Density 0.058%

    No Known Activations