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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “question‐answering” (i.e. occurrences of “question” in the context of asking or answering).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Biography
    -0.07
    .Tags
    -0.06
    _itr
    -0.06
    _BOLD
    -0.06
     Stanton
    -0.06
    Other
    -0.06
     кус
    -0.06
     bites
    -0.06
    179
    -0.06
    HeaderText
    -0.06
    POSITIVE LOGITS
    ание
    0.07
    cek
    0.07
    افت
    0.07
    ностей
    0.07
    anic
    0.06
    ně
    0.06
    احة
    0.06
    box
    0.06
    英雄
    0.06
    startdate
    0.06
    Act Density 0.008%

    No Known Activations