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

    Neuronpedia

    INDEX
    Explanations

    instances of high-importance code segments or operations

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

    multiplication symbols and dashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁣
    -0.47
     BoxDecoration
    -0.43
    InstanceState
    -0.42
    ThemeOverlay
    -0.42
    ➟
    -0.40
    randomUUID
    -0.40
    ë
    -0.40
     thêm
    -0.38
    cticut
    -0.38
    ower
    -0.38
    POSITIVE LOGITS
    <?
    0.66
    -------
    0.57
     للمعارف
    0.55
    ########.
    0.54
     كومونز
    0.53
     AssemblyTitle
    0.53
    AlterField
    0.52
     AssemblyCompany
    0.52
     daß
    0.50
     الحره
    0.48
    Act Density 0.175%

    No Known Activations