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

    Neuronpedia

    INDEX
    Explanations

    references to governmental or military organizations and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Guard, Service, spill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.55
     يتيمه
    -0.40
    PerformLayout
    -0.40
    Hauptartikel
    -0.39
     kasarigan
    -0.38
    imwrite
    -0.36
     مُعرِّف
    -0.35
    AdapterView
    -0.35
     Speise
    -0.34
    Será
    -0.34
    POSITIVE LOGITS
     Guard
    0.87
     GUARD
    0.66
    Guard
    0.64
    Navy
    0.62
    liferay
    0.62
     maritime
    0.62
     Boating
    0.60
     Coast
    0.59
     Marine
    0.59
     Navy
    0.59
    Act Density 0.004%

    No Known Activations