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

    Neuronpedia

    INDEX
    Explanations

    document root

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Redis
    0.47
     headless
    0.46
     PostgreSQL
    0.43
    nginx
    0.43
    Redis
    0.43
     Updater
    0.43
    FontStyle
    0.42
     SSH
    0.42
     nginx
    0.42
     json
    0.41
    POSITIVE LOGITS
    root
    0.70
     root
    0.70
     roots
    0.66
    roots
    0.63
     ROOT
    0.63
     rooting
    0.61
     Root
    0.60
    根
    0.60
    setRoot
    0.58
    ROOT
    0.55
    Act Density 0.006%

    No Known Activations