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

    Neuronpedia

    INDEX
    Explanations

    extracting specific data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вы
    0.94
     Эк
    0.93
     Кы
    0.84
     Εκ
    0.82
     Э
    0.81
     amerikanischen
    0.81
     Electroly
    0.80
     Это
    0.79
     dọc
    0.79
     Кра
    0.78
    POSITIVE LOGITS
    clothing
    0.86
    brough
    0.86
    fashion
    0.82
    भवती
    0.81
    edges
    0.79
    carrier
    0.79
    cloud
    0.79
    interrupt
    0.77
    cutter
    0.77
    trust
    0.77
    Act Density 0.000%

    No Known Activations