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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lopez
    -0.07
     Wishlist
    -0.07
     Athena
    -0.07
     **/↵↵
    -0.07
     "/";↵
    -0.07
     لتح
    -0.07
    细微
    -0.07
    amaha
    -0.07
    โฮ
    -0.07
    Chance
    -0.06
    POSITIVE LOGITS
    יאות
    0.08
     ethical
    0.07
    耽
    0.07
     astro
    0.07
    人生
    0.07
    🍎
    0.07
    essions
    0.07
    Email
    0.07
    意
    0.07
     chồng
    0.07
    Act Density 0.010%

    No Known Activations