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

    Neuronpedia

    INDEX
    Explanations

    business locations/descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase pattern “a chemical company in” (i.e., introductions naming a chemical company’s location).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     جدید
    -0.07
     cosas
    -0.06
     libros
    -0.06
    while
    -0.06
    lemma
    -0.06
     kuchy
    -0.06
    ocide
    -0.06
     gode
    -0.06
    岳
    -0.06
    _POINTER
    -0.06
    POSITIVE LOGITS
    Comparable
    0.07
     PodsDummy
    0.06
     acquainted
    0.06
    Classic
    0.06
     орг
    0.06
     Audrey
    0.06
    Previously
    0.06
    .rotate
    0.06
    general
    0.06
    を見る
    0.06
    Act Density 0.019%

    No Known Activations