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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adhy
    0.54
     McQu
    0.50
     المك
    0.47
    দিগকে
    0.46
    READER
    0.46
     Müdür
    0.46
    Shen
    0.46
     Dewar
    0.46
    ！」
    0.45
    Pp
    0.45
    POSITIVE LOGITS
     called
    0.51
     cracks
    0.50
     advances
    0.48
     arg
    0.47
     fits
    0.46
    1
    0.45
     races
    0.45
     clarification
    0.43
     seper
    0.43
     {
    0.43
    Act Density 0.006%

    No Known Activations