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

    Neuronpedia

    INDEX
    Explanations

    watch and guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pcion
    0.49
    掌握
    0.46
    u
    0.46
    djang
    0.45
    vas
    0.45
    िकेटेड
    0.45
     florist
    0.44
     darstellen
    0.44
    volt
    0.44
    MISSIONS
    0.44
    POSITIVE LOGITS
     watch
    0.86
     WATCH
    0.85
    watch
    0.81
     Watch
    0.80
     watcher
    0.80
    ウォッチ
    0.78
     watches
    0.75
     watchers
    0.72
     watchful
    0.70
     Watching
    0.69
    Act Density 0.024%

    No Known Activations