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

    Neuronpedia

    INDEX
    Explanations

    assuming today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Qué
    0.75
    Entertainment
    0.71
     ostensibly
    0.71
     filóso
    0.68
    许多
    0.67
     econôm
    0.67
     insofar
    0.67
     etcétera
    0.66
     comenzó
    0.66
    ––
    0.66
    POSITIVE LOGITS
     upto
    1.28
     atleast
    1.06
     same
    0.95
     everytime
    0.94
     equipments
    0.93
     saree
    0.88
     squre
    0.87
     softwares
    0.86
     sarees
    0.84
     dataframe
    0.82
    Act Density 0.002%

    No Known Activations