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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron fires on attribute names (and their values) inside angle-bracketed tags (e.g. AutoPostBack, RepeatDirection, AutoGenerateColumns in ASP/HTML/XML markup).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    imited
    -0.07
    andre
    -0.07
    GUID
    -0.07
     enrich
    -0.06
     materially
    -0.06
    .TextImageRelation
    -0.06
     sorted
    -0.06
    _variant
    -0.06
    에
    -0.06
     PB
    -0.06
    POSITIVE LOGITS
    fee
    0.07
    .Design
    0.07
    eways
    0.07
    ocaly
    0.06
    duino
    0.06
     �
    0.06
     卡
    0.06
    πό
    0.06
     lesbische
    0.06
    rios
    0.06
    Act Density 0.004%

    No Known Activations