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

    Neuronpedia

    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on Korean enumeration or listing markers (words like “다양한,” “등,” etc.) that introduce or conclude itemized lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    History
    -0.07
     voc
    -0.07
     /(
    -0.07
    Configuration
    -0.07
    .devices
    -0.07
    registration
    -0.07
     العالمية
    -0.07
     ());↵↵
    -0.07
    GetInstance
    -0.06
    audit
    -0.06
    POSITIVE LOGITS
     sach
    0.07
    ZA
    0.06
    などの
    0.06
    (DATA
    0.06
     Cool
    0.06
    ROAD
    0.06
    LLL
    0.06
    等
    0.06
    čin
    0.06
    ільш
    0.05
    Act Density 0.018%

    No Known Activations