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

    Neuronpedia

    INDEX
    Explanations

    instructions/explanations

    np_max-act · gemini-2.0-flash

    The neuron detects JSDoc-style documentation markers in code comments (e.g. lines beginning with “@” tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ツ
    -0.07
    _);
↵
    -0.06
    _Number
    -0.06
    ;++
    -0.06
    (dictionary
    -0.06
     consumption
    -0.06
     terminals
    -0.06
     bronze
    -0.06
    WhatsApp
    -0.06
    _PAYLOAD
    -0.06
    POSITIVE LOGITS
    aporation
    0.07
    리는
    0.07
     ΠΑΝ
    0.07
    하는
    0.06
    ”?
    0.06
    리
    0.06
     #(
    0.06
    ��
    0.06
    	me
    0.06
     développement
    0.06
    Act Density 0.133%

    No Known Activations