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

    Neuronpedia

    INDEX
    Explanations

    Last names

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized proper names, especially individual people’s names (e.g. players, managers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     activism
    -0.06
    mx
    -0.06
    cis
    -0.06
     Gay
    -0.06
     cyber
    -0.05
     над
    -0.05
    istan
    -0.05
    ク
    -0.05
     Boom
    -0.05
     puzzles
    -0.05
    POSITIVE LOGITS
    _Pos
    0.08
    .hasNext
    0.07
    _memcpy
    0.07
    _vehicle
    0.07
     killed
    0.07
    \Page
    0.07
     JObject
    0.07
    .fields
    0.07
    .Cells
    0.07
    문화
    0.06
    Act Density 0.024%

    No Known Activations