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

    Neuronpedia

    INDEX
    Explanations

    yourself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    صة
    -0.07
    望
    -0.06
     Yani
    -0.06
    -exp
    -0.06
    oble
    -0.06
     datas
    -0.06
     LES
    -0.06
     cultured
    -0.06
     transmission
    -0.06
     Chemical
    -0.06
    POSITIVE LOGITS
    omore
    0.07
    Enjoy
    0.06
     вор
    0.06
         
↵
    0.06
    EditMode
    0.06
    Image
    0.06
     toc
    0.06
     diminishing
    0.06
     Celebration
    0.06
    ouncill
    0.06
    Act Density 0.004%

    No Known Activations