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

    Neuronpedia

    INDEX
    Explanations

    restrictions/prohibitions

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens, especially floating-point number fragments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     그것
    -0.09
     UR
    -0.07
    AdapterManager
    -0.06
    Ok
    -0.06
    튼
    -0.06
     legitimate
    -0.06
    选择
    -0.06
     visitors
    -0.06
    .getBy
    -0.06
    _plain
    -0.06
    POSITIVE LOGITS
     Torrent
    0.06
     Aug
    0.06
    acia
    0.06
    maid
    0.06
    غير
    0.06
    ublished
    0.06
    atoire
    0.06
    源
    0.06
    pany
    0.06
     QR
    0.06
    Act Density 0.059%

    No Known Activations