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

    Neuronpedia

    INDEX
    Explanations

    championships

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the phrase “World Championships” (i.e. it fires on the words “World” and “Championships” in event titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     але
    -0.07
    Poll
    -0.07
    มากกว
    -0.06
    旅游
    -0.06
     vị
    -0.06
     CultureInfo
    -0.06
    调
    -0.06
     cheerful
    -0.06
     mong
    -0.06
    _active
    -0.06
    POSITIVE LOGITS
    hasil
    0.07
    aires
    0.07
    acio
    0.06
     fim
    0.06
    HR
    0.06
    azione
    0.06
    shift
    0.06
     Darling
    0.06
    里面
    0.06
     ücret
    0.06
    Act Density 0.004%

    No Known Activations