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

    Neuronpedia

    INDEX
    Explanations

    names and dates

    np_max-act · gemini-2.0-flash

    The neuron activates on fragments of personal proper names—especially surnames and hyphenated name parts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    names and titles of historical figures and their roles or positions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    'options
    -0.06
    )\↵
    -0.06
     tav
    -0.06
    (training
    -0.06
     mutations
    -0.06
     кноп
    -0.06
    جو
    -0.06
    úng
    -0.06
     memory
    -0.06
    .dll
    -0.06
    POSITIVE LOGITS
     Bik
    0.07
     younger
    0.06
    |wx
    0.06
    +x
    0.06
     بم
    0.06
     neust
    0.06
    (wx
    0.06
    itious
    0.06
     zeal
    0.06
     Wrong
    0.06
    Act Density 0.061%

    No Known Activations