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

    Neuronpedia

    INDEX
    Explanations

    unreadable text in research

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the token “unread” (as in “[unreadable]”) marking unreadable text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erty
    -0.07
    _clip
    -0.07
    gain
    -0.06
    (visitor
    -0.06
    isté
    -0.06
     Kurum
    -0.06
     EITHER
    -0.06
    acades
    -0.06
    inizi
    -0.06
     visibly
    -0.06
    POSITIVE LOGITS
     یاد
    0.07
    dataArray
    0.06
     Rick
    0.06
    unread
    0.06
    |{↵
    0.06
    Expert
    0.06
     block
    0.06
     printable
    0.06
     coded
    0.06
     пен
    0.06
    Act Density 0.000%

    No Known Activations