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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on the assistant’s response header or speaker‐attribution markers (e.g. the “AIM:” prefix and surrounding metadata tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     drivers
    -0.07
     Brush
    -0.07
    Ticker
    -0.07
    _PARENT
    -0.06
    落ち
    -0.06
    Money
    -0.06
    uye
    -0.06
     pastors
    -0.06
    ski
    -0.06
     postings
    -0.06
    POSITIVE LOGITS
    .youtube
    0.07
    @media
    0.07
    921
    0.06
    ,uint
    0.06
    окумент
    0.06
    these
    0.06
     elbows
    0.06
    UDP
    0.06
    ₃
    0.06
     červ
    0.06
    Act Density 0.002%

    No Known Activations