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

    Neuronpedia

    INDEX
    Explanations

    Thomas Jefferson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    у
    0.75
    ě
    0.68
    0.63
    ся
    0.61
    ᥱ
    0.61
    ég
    0.60
     توزيع
    0.60
     هناك
    0.59
    шему
    0.59
    ит
    0.59
    POSITIVE LOGITS
    TINGS
    0.73
    ।
    0.69
    ।)
    0.66
    叅
    0.66
    )%>%
    0.61
     clara
    0.61
    )\
    0.58
    )!
    0.58
    <=>
    0.58
    mgr
    0.57
    Act Density 0.001%

    No Known Activations