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

    Neuronpedia

    INDEX
    Explanations

    phrases related to alarm and alertness features in applications

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

    user account renewal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.76
     estekak
    -0.69
    expandindo
    -0.67
    SourceChecksum
    -0.62
    TargetException
    -0.61
    帖最后由
    -0.60
    principalTable
    -0.58
     resourceCulture
    -0.56
     questioned
    -0.55
    Ārējās
    -0.55
    POSITIVE LOGITS
     user
    0.37
     users
    0.35
     your
    0.35
     app
    0.34
     kids
    0.34
     Android
    0.32
     User
    0.32
    !
    0.31
    Pixel
    0.31
     you
    0.31
    Act Density 0.011%

    No Known Activations