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

    Neuronpedia

    INDEX
    Explanations

    java import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Injection
    0.77
    io
    0.77
    Pipeline
    0.77
    Docker
    0.77
    com
    0.75
    Platform
    0.74
    App
    0.74
    coroutines
    0.74
    Ancient
    0.74
    Com
    0.74
    POSITIVE LOGITS
     surpass
    1.01
     javafx
    0.98
     suppl
    0.97
     ballads
    0.97
     sentimental
    0.96
     ballad
    0.92
     GUI
    0.92
     จ
    0.92
     viewed
    0.91
     mäng
    0.91
    Act Density 0.002%

    No Known Activations