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

    Neuronpedia

    INDEX
    Explanations

    version releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ortalama
    -0.07
    ForResult
    -0.07
    	Run
    -0.07
     Prevention
    -0.07
     RoundedRectangle
    -0.06
    Assembler
    -0.06
     Champions
    -0.06
     salah
    -0.06
     мм
    -0.06
     homework
    -0.06
    POSITIVE LOGITS
    .exp
    0.07
    етель
    0.06
     xi
    0.06
     giving
    0.06
     ruth
    0.06
     sext
    0.06
    ');↵↵↵↵
    0.06
     authorised
    0.06
    cribes
    0.06
    _stage
    0.06
    Act Density 0.013%

    No Known Activations