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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that look like the dot‐separated local‐part of email addresses (e.g. name.initial).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    δος
    -0.07
     Tôi
    -0.07
    ord
    -0.07
     Drop
    -0.07
    arter
    -0.06
     Vir
    -0.06
     Welcome
    -0.06
    #for
    -0.06
    リア
    -0.06
    tableView
    -0.06
    POSITIVE LOGITS
     ",");↵
    0.07
    .="<
    0.07
    이가
    0.07
     ελλην
    0.06
    .readline
    0.06
    كو
    0.06
     söylem
    0.06
    .amazon
    0.06
    ��
    0.06
     sonucunda
    0.06
    Act Density 0.004%

    No Known Activations