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

    Neuronpedia

    INDEX
    Explanations

    exercise routines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuck
    -0.07
     elong
    -0.07
     Эти
    -0.06
    “As
    -0.06
     pazar
    -0.06
    FTP
    -0.06
     사진
    -0.06
    混合
    -0.06
    -chief
    -0.06
     corpo
    -0.06
    POSITIVE LOGITS
    ="">↵
    0.07
    	module
    0.07
    Australia
    0.06
     Rentals
    0.06
    (child
    0.06
    дяки
    0.06
     Ghost
    0.06
    Spec
    0.06
    势
    0.06
    .Version
    0.06
    Act Density 0.004%

    No Known Activations