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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    This neuron detects question phrases expressing a search for information—especially the words “any” and “information” in queries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IMF
    -0.07
    鮮
    -0.07
    (Have
    -0.07
     threaten
    -0.07
    _Resource
    -0.06
    VectorXd
    -0.06
    公開
    -0.06
     rá
    -0.06
     antioxidants
    -0.06
     Sark
    -0.06
    POSITIVE LOGITS
     find
    0.07
    они
    0.06
     nâng
    0.06
    см
    0.06
    权限
    0.06
    ística
    0.06
     '-',
    0.06
    Console
    0.06
     Spy
    0.06
    оне
    0.06
    Act Density 0.016%

    No Known Activations