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

    Neuronpedia

    INDEX
    Explanations

    Global

    np_max-act · gemini-2.0-flash

    The neuron responds to the word “global.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     seventeen
    -0.08
     Pee
    -0.08
     ink
    -0.07
    tte
    -0.07
     erected
    -0.07
    丁目
    -0.07
    erne
    -0.07
    に出
    -0.07
    сті
    -0.06
    ע
    -0.06
    POSITIVE LOGITS
     Global
    0.16
     global
    0.14
    Global
    0.12
     GLOBAL
    0.11
     globally
    0.10
    global
    0.09
    GLOBAL
    0.08
    _global
    0.08
    	Global
    0.08
    _GLOBAL
    0.08
    Act Density 0.011%

    No Known Activations