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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash

    This neuron fires on the initial single-character uppercase token at the start of a document’s title or proper‐noun heading.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     바이
    -0.07
     То
    -0.07
     sourceMapping
    -0.06
     ActionType
    -0.06
    	Page
    -0.06
     Must
    -0.06
     onemocnění
    -0.06
     exited
    -0.06
     Kostenlos
    -0.06
     brunch
    -0.06
    POSITIVE LOGITS
     tolerated
    0.06
    FlatButton
    0.06
    ryn
    0.06
    .getAttribute
    0.06
    -point
    0.06
     volume
    0.06
    .channel
    0.06
    delete
    0.06
     мест
    0.06
    ины
    0.06
    Act Density 0.013%

    No Known Activations