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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xaa
    -0.07
    ii
    -0.07
    (Window
    -0.07
     maneuvers
    -0.07
    ray
    -0.07
    Image
    -0.07
    pa
    -0.06
     Nb
    -0.06
    *)_
    -0.06
    解决方案
    -0.06
    POSITIVE LOGITS
    ";}↵
    0.08
     *</
    0.07
    ܤ
    0.07
     unos
    0.07
     typedef
    0.07
    普京
    0.07
                 ↵
    0.07
     автор
    0.07
     ';
↵
    0.07
    					
↵
    0.07
    Act Density 0.011%

    No Known Activations