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

    Neuronpedia

    INDEX
    Explanations

    a former, a living

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.78
     অথবা
    0.76
     কিংবা
    0.71
    或者
    0.69
     either
    0.69
     或
    0.68
     หรือ
    0.67
     или
    0.67
     અથવા
    0.67
     Skyrim
    0.67
    POSITIVE LOGITS
    meisterschaft
    0.95
     izgleda
    0.93
     fyra
    0.90
    botao
    0.90
     философия
    0.89
    müş
    0.89
     famously
    0.89
     eponymous
    0.89
     perhitungan
    0.88
     czter
    0.87
    Act Density 0.334%

    No Known Activations