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

    Neuronpedia

    INDEX
    Explanations

    rivers

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a river’s width—phrases like “más ancho,” “anchura,” numeric measurements in kilometers, and related descriptors of how wide a river is.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information about major rivers and their characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ाण
    -0.07
    (writer
    -0.07
    ابع
    -0.06
     modules
    -0.06
    쪽
    -0.06
     aldı
    -0.06
    ैय
    -0.06
    BUFF
    -0.06
    dana
    -0.06
    نویس
    -0.06
    POSITIVE LOGITS
    pun
    0.07
     question
    0.06
     Spy
    0.06
    �
    0.06
     funky
    0.06
    .JScrollPane
    0.06
     predicts
    0.06
    unic
    0.06
     Sep
    0.06
    =[
    0.06
    Act Density 0.026%

    No Known Activations