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

    Neuronpedia

    INDEX
    Explanations

    London Underground ("tube")

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find references to public‐transport access (e.g. tube/metro lines, stations, and related transit directions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TestCase
    -0.07
     источ
    -0.06
    rys
    -0.06
    ethnic
    -0.06
    '])){
    -0.06
    ocations
    -0.06
    shop
    -0.06
    лоп
    -0.06
    еріга
    -0.06
    /plain
    -0.06
    POSITIVE LOGITS
     crossorigin
    0.07
     ",↵
    0.07
    ...",↵
    0.07
     bursts
    0.06
    Recipient
    0.06
     intersects
    0.06
    인가
    0.06
    patibility
    0.06
    ASTER
    0.06
    	Method
    0.06
    Act Density 0.015%

    No Known Activations