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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific contexts

    np_max-act · gemini-2.0-flash

    tokens that appear in assistant-generated reply text (i.e., content produced by the assistant).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    駅徒歩
    -0.06
    ^^
    -0.06
    #if
    -0.06
     Skywalker
    -0.06
    ))))
    -0.06
     layouts
    -0.06
     перева
    -0.06
    Tem
    -0.06
    .setValue
    -0.06
     заклад
    -0.06
    POSITIVE LOGITS
     sexe
    0.07
     categor
    0.06
    roken
    0.06
     Det
    0.06
    .Ac
    0.06
    OOD
    0.06
    _NS
    0.06
     Theatre
    0.06
    extract
    0.06
    境
    0.06
    Act Density 0.536%

    No Known Activations