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

    Neuronpedia

    INDEX
    Explanations

    groupings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typescript
    -0.07
    .Restr
    -0.07
    ніверсит
    -0.06
     男
    -0.06
     美国
    -0.06
    *ft
    -0.06
     restau
    -0.06
     vind
    -0.06
     Sala
    -0.06
    (ll
    -0.06
    POSITIVE LOGITS
    酒店
    0.07
    Colors
    0.06
    ↵            
↵
    0.06
     Supplier
    0.06
    _ENCODING
    0.06
    ayacak
    0.06
     manip
    0.06
     Specifications
    0.06
    "]),↵
    0.06
    
    0.06
    Act Density 0.081%

    No Known Activations