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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    This neuron detects the special header‐ID delimiter tokens that mark the beginnings of metadata blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ｰ
    -0.06
    [end
    -0.06
    :]:↵
    -0.06
     الأف
    -0.06
    (){↵↵
    -0.06
    _buy
    -0.06
     petals
    -0.06
     度
    -0.06
    -enh
    -0.06
    ्यत
    -0.06
    POSITIVE LOGITS
    string
    0.07
     Spectrum
    0.07
    емати
    0.06
     mostrar
    0.06
    	String
    0.06
    .trace
    0.06
     mı
    0.06
    (attribute
    0.06
    tooltip
    0.06
    (defun
    0.06
    Act Density 0.024%

    No Known Activations