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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of key scientific terms and concepts

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

    software development and technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects sequence or turn boundaries (tokens marking the end of a turn / end of the document).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     <>",
    -0.62
     للاسماء
    -0.56
    Autoritní
    -0.53
    клопе
    -0.52
     Palacios
    -0.47
    MemoryWarning
    -0.47
     Parkes
    -0.46
     nahilalakip
    -0.46
     Stellung
    -0.45
     lilies
    -0.45
    POSITIVE LOGITS
     FontWeight
    0.48
    CppMethod
    0.43
    onAttach
    0.40
    /).
    0.38
    ).
    0.35
    ).\\
    0.35
     hObject
    0.35
    RenderAtEndOf
    0.34
    ).}
    0.34
    %).
    0.33
    Act Density 0.318%

    No Known Activations