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

    Neuronpedia

    INDEX
    Explanations

    any data type or object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numArray
    0.48
     названия
    0.43
    肌肉
    0.42
    铜
    0.40
    भूमी
    0.40
     három
    0.39
     পর্বত
    0.39
    試合
    0.39
     четырех
    0.38
    壹百
    0.38
    POSITIVE LOGITS
     objects
    0.95
     object
    0.87
    对象
    0.80
     объекта
    0.76
    Object
    0.75
     objek
    0.75
     Objects
    0.74
     Object
    0.74
     objetos
    0.74
     объектов
    0.74
    Act Density 0.065%

    No Known Activations