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

    Neuronpedia

    INDEX
    Explanations

    sea straits and passages

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific narrow waterways (e.g., “Strait,” “Passage”) by activating on their geographic names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cons
    -0.07
     Viol
    -0.06
     Choir
    -0.06
    产品
    -0.06
    t
    -0.06
    /qu
    -0.06
     CBC
    -0.06
    -address
    -0.06
    \\
    -0.06
     DEFIN
    -0.06
    POSITIVE LOGITS
    를
    0.07
     convincing
    0.06
     archivos
    0.06
    λό
    0.06
     seasoned
    0.06
     trải
    0.06
     compression
    0.06
    seo
    0.06
     Managed
    0.06
     společnosti
    0.06
    Act Density 0.008%

    No Known Activations