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

    Neuronpedia

    INDEX
    Explanations

    silence

    np_max-act · gemini-2.0-flash

    This neuron detects words that describe or evoke quietness and stillness (e.g., “eerily,” “quiet,” “silent”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    吐
    -0.08
    也
    -0.07
    zbek
    -0.06
    PLIT
    -0.06
    (news
    -0.06
    icos
    -0.06
    hb
    -0.06
    _Def
    -0.06
     borderColor
    -0.06
    딩
    -0.06
    POSITIVE LOGITS
    伤
    0.07
    addPreferredGap
    0.06
     Warehouse
    0.06
     Pier
    0.06
     halves
    0.06
    .springframework
    0.06
     ensuring
    0.06
     Seriously
    0.06
     apprentices
    0.06
     boring
    0.06
    Act Density 0.022%

    No Known Activations