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

    Neuronpedia

    INDEX
    Explanations

    code comments and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ط
    0.39
     Ан
    0.38
     Java
    0.37
     JPA
    0.36
     erscheinen
    0.36
     Jacobi
    0.36
    حل
    0.35
     যু
    0.35
    btnPrint
    0.35
     JAVA
    0.35
    POSITIVE LOGITS
    cars
    0.46
     நன்றி
    0.45
     nyní
    0.42
    ยน
    0.41
    >:
    0.40
    不会
    0.39
    PrefabInstance
    0.39
    Automat
    0.39
     शुक्रिया
    0.38
     ahorita
    0.38
    Act Density 0.003%

    No Known Activations