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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash

    This neuron detects polite greeting and introductory phrases used when initiating a phone‐call conversation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Seek
    -0.07
     궁
    -0.07
    /de
    -0.06
    าถ
    -0.06
     prázd
    -0.06
    008
    -0.06
     Summers
    -0.06
     رح
    -0.06
    mAh
    -0.06
    重要
    -0.06
    POSITIVE LOGITS
     искус
    0.07
     '!
    0.06
    _enabled
    0.06
     اقتصادی
    0.06
     نمایش
    0.06
    _adv
    0.06
     oranı
    0.06
    .feature
    0.06
     disagreements
    0.06
     storing
    0.06
    Act Density 0.010%

    No Known Activations