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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron detects documentation-style phrases that describe returned data structures (e.g. “list of tuples where each tuple contains…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Supply
    -0.07
    Gallery
    -0.07
    Employ
    -0.07
    Codigo
    -0.07
    Action
    -0.07
     butter
    -0.06
     STANDARD
    -0.06
     supply
    -0.06
    Emily
    -0.06
    Luke
    -0.06
    POSITIVE LOGITS
     등의
    0.07
     corresponds
    0.06
    (($
    0.06
     Лі
    0.06
    .DisplayMember
    0.06
     rss
    0.06
     hız
    0.06
     مسئول
    0.06
     drinkers
    0.06
    interested
    0.06
    Act Density 0.026%

    No Known Activations