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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duration or timeframes

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

    time until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stanga
    -0.39
    pageX
    -0.32
     simb
    -0.31
    ض
    -0.30
    拿着
    -0.29
    ResponseType
    -0.29
    CardNumber
    -0.28
    TotalCount
    -0.28
    ドゥ
    -0.28
    าน
    -0.27
    POSITIVE LOGITS
    ConstraintMaker
    0.90
    IntoConstraints
    0.85
    RegressionTest
    0.80
     AssemblyCompany
    0.79
     until
    0.78
    PostInfinity
    0.75
     فريبيس
    0.74
    elemField
    0.74
     يتيمه
    0.73
     SwitchCompat
    0.73
    Act Density 0.011%

    No Known Activations