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

    Neuronpedia

    INDEX
    Explanations

    Weddings

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on numbered list markers and document outline numerals (e.g. “1.”, “2.”, chapter or section numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fo
    -0.07
    дем
    -0.06
     захід
    -0.06
     青
    -0.06
    _call
    -0.06
     broadcaster
    -0.06
     밤
    -0.06
     Penn
    -0.06
    avě
    -0.06
    heard
    -0.06
    POSITIVE LOGITS
    zhou
    0.06
    SSIP
    0.06
    汇
    0.06
     galer
    0.06
    ories
    0.06
    BT
    0.06
    _Pods
    0.06
    考试
    0.06
    ระเบ
    0.06
     стос
    0.06
    Act Density 0.033%

    No Known Activations