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

    Neuronpedia

    INDEX
    Explanations

    JSON serialization/deserialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ฟัง
    0.41
    itate
    0.40
     Analysis
    0.40
    0.39
     besten
    0.39
     نوشت
    0.38
     analizar
    0.38
     quoted
    0.38
    TabView
    0.37
     bete
    0.37
    POSITIVE LOGITS
     сер
    0.44
    Serializer
    0.44
    织
    0.43
     ser
    0.43
    serializer
    0.41
    ser
    0.41
    OnInit
    0.41
    ГИ
    0.41
     serial
    0.40
    整体
    0.39
    Act Density 0.002%

    No Known Activations