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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alibaba
    -0.07
     performans
    -0.07
     ●
    -0.07
    }?
    -0.07
    FontSize
    -0.07
     центр
    -0.06
    apps
    -0.06
     pneumonia
    -0.06
     {
↵
    -0.06
     서비스
    -0.06
    POSITIVE LOGITS
     Cousins
    0.07
     cousin
    0.06
     Mourinho
    0.06
     creatures
    0.06
     typed
    0.06
     monsters
    0.06
     Lancaster
    0.06
     homemade
    0.06
     malaysia
    0.06
    การส
    0.06
    Act Density 0.046%

    No Known Activations