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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    The neuron activates on proper names—distinct capitalized entities like people’s names, place names, or organization abbreviations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    UND
    -0.07
    VENTORY
    -0.07
     manipulate
    -0.07
    jury
    -0.07
    ING
    -0.06
     ')↵↵
    -0.06
       ↵
    -0.06
    -average
    -0.06
    ходить
    -0.06
    ↵    ↵
    -0.06
    POSITIVE LOGITS
    <dim
    0.07
    unny
    0.07
     arbe
    0.06
    zek
    0.06
     indispens
    0.06
     cuk
    0.06
    주소
    0.06
    stroy
    0.06
    .setForeground
    0.06
    boys
    0.06
    Act Density 0.045%

    No Known Activations