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

    Neuronpedia

    INDEX
    Explanations

    store list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    2.47
    ore
    1.93
    stes
    1.91
    ain
    1.83
    st
    1.82
    ן
    1.81
    riding
    1.80
    stud
    1.78
    ng
    1.77
    sp
    1.75
    POSITIVE LOGITS
    هن
    1.93
    ‌ی
    1.92
    e
    1.90
    логии
    1.67
    eid
    1.67
    ‌ای
    1.61
    ERSON
    1.56
    ි
    1.56
    ನ್
    1.55
     Ў
    1.55
    Act Density 0.045%

    No Known Activations