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

    Neuronpedia

    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash

    the neuron detects when the text is referring to JavaScript (e.g. “JavaScript,” “JS,” or related mentions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	boost
    -0.08
     текущ
    -0.07
    ");
↵
    -0.07
    ixel
    -0.07
    simulate
    -0.06
    盗
    -0.06
     помощ
    -0.06
    	buff
    -0.06
     Cambridge
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
    ائلة
    0.07
     appel
    0.07
    #\
    0.06
     niños
    0.06
     phased
    0.06
     cấp
    0.06
     glass
    0.06
     entityManager
    0.06
    ž
    0.06
     horn
    0.06
    Act Density 0.018%

    No Known Activations