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
     comprehend
    -0.07
    .gridView
    -0.07
    ा↵
    -0.07
    ालय
    -0.07
    或者
    -0.06
    ительным
    -0.06
     آموزشی
    -0.06
     gratuiti
    -0.06
    /Table
    -0.06
     ن
    -0.06
    POSITIVE LOGITS
     representing
    0.07
     PCs
    0.06
     Michelle
    0.06
    SERVER
    0.06
     dept
    0.06
     spole
    0.06
     deren
    0.06
     helmets
    0.06
     bass
    0.06
    Michelle
    0.06
    Act Density 0.050%

    No Known Activations