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

    Neuronpedia

    INDEX
    Explanations

    scientific analysis

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on technical, procedural language describing methods and analyses (e.g. “was carried out,” statistical or experimental procedure passages).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     minut
    -0.06
     honoured
    -0.06
     ilç
    -0.06
     kho
    -0.06
     Alvarez
    -0.06
     lil
    -0.06
     Ka
    -0.06
     orange
    -0.06
     IA
    -0.06
     dishes
    -0.06
    POSITIVE LOGITS
    .Println
    0.07
    _SUPPORT
    0.06
    HDATA
    0.06
    {|
    0.06
    advert
    0.06
     ajout
    0.06
    -caret
    0.06
     Establishment
    0.06
    .extensions
    0.06
    ği
    0.06
    Act Density 0.040%

    No Known Activations