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

    Neuronpedia

    INDEX
    Explanations

    references to passwords and password-related actions

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

    password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dage
    -0.44
    KommentareTeilen
    -0.44
    試試
    -0.44
    protoc
    -0.41
    iolis
    -0.40
    hatic
    -0.40
     polarization
    -0.40
    ixe
    -0.40
     romance
    -0.40
     Hook
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.49
     المعيارى
    0.45
    expandindo
    0.44
    ViewImports
    0.41
     NUKAT
    0.40
     oms
    0.39
    bewerken
    0.38
     uLocal
    0.37
    tagHelperRunner
    0.37
     bezw
    0.35
    Act Density 0.001%

    No Known Activations