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

    Neuronpedia

    INDEX
    Explanations

    .Xaml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plush
    -0.10
     gifs
    -0.08
    ,content
    -0.07
    果
    -0.07
    若
    -0.07
     pony
    -0.06
    段
    -0.06
    (display
    -0.06
     forte
    -0.06
    폐
    -0.06
    POSITIVE LOGITS
     Business
    0.08
    inction
    0.07
     usual
    0.07
     October
    0.07
    それでも
    0.07
     bingo
    0.07
     médico
    0.07
    랔
    0.07
     Internal
    0.07
    끓
    0.06
    Act Density 0.001%

    No Known Activations