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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects references to online resources, specifically web links or URLs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Oro
    -0.07
     py
    -0.06
    的时候
    -0.06
     perception
    -0.06
    ook
    -0.06
    601
    -0.06
    ości
    -0.06
    airport
    -0.06
     Leaf
    -0.06
     beach
    -0.06
    POSITIVE LOGITS
     biting
    0.07
    Servers
    0.07
    Women
    0.07
    .bt
    0.07
     carved
    0.06
     sway
    0.06
    (true
    0.06
     Οκ
    0.06
    合格
    0.06
    Labor
    0.06
    Act Density 0.014%

    No Known Activations