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

    Neuronpedia

    INDEX
    Explanations

    Code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jul
    -0.07
     позитив
    -0.07
    torch
    -0.07
     REAL
    -0.06
    (Conv
    -0.06
     apl
    -0.06
     drastically
    -0.06
     Modules
    -0.06
    warning
    -0.06
     jo
    -0.06
    POSITIVE LOGITS
    .“↵↵
    0.07
     Etsy
    0.07
    样子
    0.06
     tavern
    0.06
    吉
    0.06
     Fiesta
    0.06
     locationManager
    0.06
     Thailand
    0.06
    ")));
↵
    0.06
    .');
↵
    0.06
    Act Density 0.003%

    No Known Activations