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

    Neuronpedia

    INDEX
    Explanations

    using Google, Cond, rem, csv, OpenCV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     armies
    0.29
    Không
    0.29
    所有
    0.29
    因為
    0.29
     모든
    0.29
    原有
    0.28
    禟
    0.28
     所有
    0.28
    водства
    0.28
     করিতে
    0.27
    POSITIVE LOGITS
     teh
    0.36
     the
    0.35
     their
    0.33
     ihrem
    0.33
     Ihrem
    0.33
     Environment
    0.31
     onboarding
    0.31
     your
    0.31
     ihrer
    0.31
    their
    0.31
    Act Density 0.054%

    No Known Activations