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

    Neuronpedia

    INDEX
    Explanations

    noise, ratio, bees, profile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأعمال
    0.94
     περισσότε
    0.92
    금
    0.90
    s
    0.89
    ▌
    0.87
    Фі
    0.86
     Mạnh
    0.86
     più
    0.84
    tır
    0.84
    人人
    0.84
    POSITIVE LOGITS
    ventions
    1.05
    ana
    0.99
     coffers
    0.98
     saith
    0.95
     naturels
    0.93
     sparkles
    0.92
     concludes
    0.91
    versed
    0.91
     obtenidos
    0.91
    peat
    0.91
    Act Density 0.008%

    No Known Activations