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

    Neuronpedia

    INDEX
    Explanations

    code structure and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     objects
    0.46
     объекты
    0.46
    objet
    0.41
     Objects
    0.40
     instantiated
    0.40
     Objekte
    0.40
     FXMLLoader
    0.39
     objeto
    0.39
     objetos
    0.39
     objets
    0.38
    POSITIVE LOGITS
    กว่า
    0.33
    业务
    0.33
    Meas
    0.33
     watched
    0.32
     ايه
    0.32
     Luckily
    0.32
    ctrl
    0.32
    gui
    0.32
    *
    0.32
     ctrl
    0.31
    Act Density 0.023%

    No Known Activations