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

    Neuronpedia

    INDEX
    Explanations

    military

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orris
    -0.28
    enny
    -0.28
    ental
    -0.27
    èĩŁ
    -0.27
    antics
    -0.26
    ìĤ°
    -0.25
    ensis
    -0.25
     sop
    -0.25
     Veter
    -0.25
    ĥģ
    -0.24
    POSITIVE LOGITS
    works
    0.29
    Works
    0.29
    ä»ĸ们æĺ¯
    0.28
     Tud
    0.26
     rods
    0.26
     Works
    0.26
     Tw
    0.25
    æĶ¿æĿĥ
    0.25
    æī§æĶ¿
    0.25
    permanent
    0.24
    Act Density 0.005%

    No Known Activations