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

    Neuronpedia

    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    난
    -0.06
    这
    -0.06
    みたい
    -0.06
     meals
    -0.06
     кла
    -0.06
    ohon
    -0.06
    isko
    -0.06
     justo
    -0.05
    iran
    -0.05
     poté
    -0.05
    POSITIVE LOGITS
     fö
    0.07
     grap
    0.07
    �
    0.06
     (__
    0.06
    333
    0.06
    ansı
    0.06
    ">//
    0.06
     remind
    0.06
     membrane
    0.06
    664
    0.06
    Act Density 0.031%

    No Known Activations