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

    Neuronpedia

    INDEX
    Explanations

    achievements and competition results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ach
    1.62
    id
    1.50
    is
    1.32
    eg
    1.29
    ari
    1.24
    q
    1.24
    ul
    1.23
    io
    1.23
    ara
    1.23
    k
    1.23
    POSITIVE LOGITS
     medals
    1.40
     medal
    1.25
     medall
    1.22
    medal
    1.19
    تان
    1.13
    ينات
    1.13
    كور
    1.13
    تين
    1.09
    لية
    1.05
     меда
    1.00
    Act Density 0.000%

    No Known Activations