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

    Neuronpedia

    INDEX
    Explanations

    Emails

    np_max-act · gemini-2.0-flash

    The neuron flags parts of the text that are email header metadata (e.g. forwarded‐by/name/date lines at the start of each forwarded block).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    arians
    -0.06
     tập
    -0.06
     теор
    -0.06
     uniqu
    -0.06
     oils
    -0.06
     í
    -0.06
     practical
    -0.06
     quasi
    -0.06
     stylist
    -0.06
    รวจ
    -0.06
    POSITIVE LOGITS
    urlencode
    0.07
    /*******************************************************************************↵
    0.07
    DidChange
    0.07
     genetically
    0.06
    /oauth
    0.06
    大學
    0.06
    اجات
    0.06
    лися
    0.06
     negatively
    0.06
    _typeof
    0.06
    Act Density 0.003%

    No Known Activations