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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations, codes, or IDs

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on short alphanumeric model‐style codes (e.g. “TL084,” “LM308,” “TL072,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .flatMap
    -0.06
     мон
    -0.06
     oversight
    -0.06
    geometry
    -0.06
    .globalData
    -0.06
     Oversight
    -0.06
     applause
    -0.06
    ीट
    -0.06
     rp
    -0.06
     rotational
    -0.06
    POSITIVE LOGITS
    аран
    0.07
     şik
    0.07
    aran
    0.07
     insiders
    0.07
    CR
    0.06
    Disclaimer
    0.06
    \Storage
    0.06
    WS
    0.06
    Forms
    0.06
     джер
    0.06
    Act Density 0.155%

    No Known Activations