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

    Neuronpedia

    INDEX
    Explanations

    big O notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INTRESOURCE
    0.41
     doctrinal
    0.41
    uelo
    0.40
    разу
    0.40
     GoObject
    0.40
    рующих
    0.40
    ին
    0.40
    ानि
    0.39
    друг
    0.39
    setTextColor
    0.39
    POSITIVE LOGITS
     kosten
    0.43
     Kosten
    0.41
    Editar
    0.40
     tarda
    0.40
     timeframe
    0.39
     através
    0.38
     unplanned
    0.38
    Quando
    0.38
    Ketika
    0.37
    С
    0.37
    Act Density 0.013%

    No Known Activations