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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    This neuron detects boundary markers—words signaling “end” or “after” (e.g. the token “end” in English and “后面” in Chinese).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    出品者
    -0.07
    олот
    -0.07
     excludes
    -0.07
    оны
    -0.06
    Gear
    -0.06
     Walking
    -0.06
     미국
    -0.06
    forg
    -0.06
    changed
    -0.06
    itches
    -0.06
    POSITIVE LOGITS
    _tasks
    0.07
     CENT
    0.06
    _SECRET
    0.06
    :last
    0.06
    brace
    0.06
     Mazda
    0.06
    .inf
    0.06
    verbosity
    0.06
    \uC
    0.06
     contend
    0.06
    Act Density 0.240%

    No Known Activations