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

    Neuronpedia

    INDEX
    Explanations

    textbook references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accommodated
    -0.07
    Authorities
    -0.07
    identi
    -0.07
     geste
    -0.07
    コミ
    -0.07
    اري
    -0.07
    tiers
    -0.07
     anonym
    -0.07
    ೀ
    -0.07
     Farmers
    -0.07
    POSITIVE LOGITS
     textbooks
    0.15
     textbook
    0.13
     tutorials
    0.11
     encyclopedia
    0.11
     encycl
    0.11
    教材
    0.10
     Encyclopedia
    0.10
     Tutorials
    0.10
    教程
    0.10
     tóp
    0.10
    Act Density 0.020%

    No Known Activations