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

    Neuronpedia

    INDEX
    Explanations

    blank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лава
    -0.07
    =W
    -0.07
    атора
    -0.07
     클래스
    -0.07
     WINDOWS
    -0.07
    Favorites
    -0.06
    Locations
    -0.06
    mma
    -0.06
     metric
    -0.06
    _sel
    -0.06
    POSITIVE LOGITS
    -group
    0.06
     Á
    0.06
     authenticated
    0.06
     ‏
    0.06
     aspir
    0.06
    ในร
    0.06
    .Hand
    0.06
     сер
    0.06
     έν
    0.06
     hob
    0.06
    Act Density 0.002%

    No Known Activations