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

    Neuronpedia

    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers and keywords (e.g. variable, type, or constant names) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cafes
    -0.07
    GPL
    -0.07
    อ
    -0.07
    غر
    -0.07
    ฺ
    -0.06
     قیمت
    -0.06
     $('#'
    -0.06
    modx
    -0.06
     Stateless
    -0.06
    (device
    -0.06
    POSITIVE LOGITS
    	className
    0.08
     stupid
    0.07
    _MASK
    0.07
    ground
    0.07
    责
    0.06
    间
    0.06
    financial
    0.06
     JSONArray
    0.06
    ousel
    0.06
    _Char
    0.06
    Act Density 0.171%

    No Known Activations