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

    Neuronpedia

    INDEX
    Explanations

    EV / Sales and Net Debt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    1.05
    nd
    0.90
    .}\
    0.87
    сть
    0.85
    िखित
    0.84
    вали
    0.84
    ня
    0.84
    adiene
    0.84
    quem
    0.83
    СТЬ
    0.83
    POSITIVE LOGITS
    いきます
    1.04
    tips
    1.02
     bahsede
    0.95
    телей
    0.93
    ဆ
    0.91
     ترا
    0.91
     waktu
    0.90
     vignettes
    0.90
     ouro
    0.89
    він
    0.88
    Act Density 0.001%

    No Known Activations