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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming, particularly in Swift and Protobuf

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

    decoding message fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beforeSend
    -0.39
    平
    -0.37
    作
    -0.35
    gesetzt
    -0.33
     Venezuela
    -0.33
    InstrumentedTest
    -0.33
     Truth
    -0.32
     Safe
    -0.32
     release
    -0.31
     peace
    -0.31
    POSITIVE LOGITS
     незавершена
    0.71
    存于互联网档案馆
    0.66
     متعلقه
    0.62
    كويكب
    0.61
    FunctionFlags
    0.60
     Meksiku
    0.60
     wireType
    0.60
    parsedMessage
    0.59
    SequentialGroup
    0.57
    :✨
    0.57
    Act Density 0.044%

    No Known Activations