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

    Neuronpedia

    INDEX
    Explanations

    language conjunctions and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.70
    ين
    0.67
    k
    0.62
    el
    0.59
    et
    0.59
    n
    0.57
    M
    0.57
    p
    0.57
    م
    0.55
    T
    0.54
    POSITIVE LOGITS
     và
    0.59
    और
    0.58
     ਅਤੇ
    0.54
     וה
    0.54
    এবং
    0.54
    महिला
    0.52
    <unused2206>
    0.50
    节日
    0.49
     ಮತ್ತು
    0.49
    emplacement
    0.49
    Act Density 0.000%

    No Known Activations