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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on the values of npm “scripts” entries—i.e. the shell‐command strings in a package.json scripts block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clans
    -0.07
     reputed
    -0.07
    Attributes
    -0.06
    ότη
    -0.06
    „ظ
    -0.06
     darn
    -0.06
    азв
    -0.06
    ,tp
    -0.06
    ker
    -0.06
     TP
    -0.06
    POSITIVE LOGITS
    _picture
    0.06
    444
    0.06
     прави
    0.06
     انتخاب
    0.06
     Xunit
    0.06
    であり
    0.06
    getClientOriginal
    0.06
    .getSelected
    0.06
    !!}↵
    0.06
    	private
    0.06
    Act Density 0.001%

    No Known Activations