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

    Neuronpedia

    INDEX
    Explanations

    places and organizations

    np_max-act · gemini-2.0-flash

    This neuron detects individual capitalized named-entity tokens—proper nouns such as place names, institutions, and personal names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    علی
    -0.07
    .fa
    -0.06
     Come
    -0.06
    .base
    -0.06
    DEFAULT
    -0.06
     удоб
    -0.06
    .sharedInstance
    -0.06
    「……
    -0.06
     icmp
    -0.06
    /tools
    -0.06
    POSITIVE LOGITS
     shall
    0.07
    lüğ
    0.06
    irling
    0.06
     odom
    0.06
     Leaving
    0.06
     тоді
    0.06
    _attrib
    0.06
     exclusively
    0.06
     Quar
    0.06
     GetData
    0.06
    Act Density 0.123%

    No Known Activations