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

    Neuronpedia

    INDEX
    Explanations

    political questioning

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “questions” (and related forms like “ask,” “asking,” etc.), i.e. explicit references to asking or framing questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tems
    -0.07
    оров
    -0.07
    Fish
    -0.07
    enny
    -0.07
     Baseball
    -0.06
    альных
    -0.06
    귀
    -0.06
     Poetry
    -0.06
     Rams
    -0.06
    習
    -0.06
    POSITIVE LOGITS
    路径
    0.06
     unc
    0.06
     clearInterval
    0.06
    asionally
    0.06
    contr
    0.06
     групи
    0.06
    /{$
    0.06
     #$
    0.06
    .condition
    0.06
    +r
    0.06
    Act Density 0.027%

    No Known Activations