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

    Neuronpedia

    INDEX
    Explanations

    manuscript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     공격
    -0.07
    traction
    -0.06
     ưu
    -0.06
    附近
    -0.06
     temperatura
    -0.06
     aantal
    -0.06
    卓
    -0.06
    -0.06
     League
    -0.06
     xảy
    -0.06
    POSITIVE LOGITS
     manuscripts
    0.14
     manuscript
    0.12
     parchment
    0.07
     Manus
    0.06
     markedly
    0.06
    -sh
    0.06
     deline
    0.06
     couldn
    0.06
    -dis
    0.06
    พย
    0.06
    Act Density 0.002%

    No Known Activations