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

    Neuronpedia

    INDEX
    Explanations

    exploit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bind
    -0.07
    Sau
    -0.07
     simplement
    -0.06
     Ash
    -0.06
     streamed
    -0.06
    Cleaning
    -0.06
    乙
    -0.06
     tern
    -0.06
    Containers
    -0.06
     Passion
    -0.06
    POSITIVE LOGITS
    /left
    0.06
    템
    0.06
     ostr
    0.06
     urged
    0.06
    [S
    0.06
     ><?
    0.06
     wrapper
    0.06
    ستم
    0.06
    !=↵
    0.06
     veniam
    0.06
    Act Density 0.007%

    No Known Activations