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

    Neuronpedia

    INDEX
    Explanations

    faith, western civilization, lasting impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.45
    q
    0.43
    n
    0.42
    pan
    0.41
    ands
    0.41
    pak
    0.41
    line
    0.41
    ó
    0.41
    agen
    0.40
    wane
    0.39
    POSITIVE LOGITS
    𝓵
    0.45
     usurp
    0.44
     في
    0.44
     prur
    0.43
     Zh
    0.43
     ஆழ்
    0.41
     yoğun
    0.41
     Herzegovina
    0.41
    Tol
    0.41
     Koš
    0.41
    Act Density 0.007%

    No Known Activations