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

    Neuronpedia

    INDEX
    Explanations

    Current events updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nguồn
    -0.08
     сет
    -0.08
       
    -0.08
    েৱ
    -0.07
    ประเทศ
    -0.07
     naquele
    -0.07
    ضي
    -0.07
    或者
    -0.07
    름
    -0.07
     หรือ
    -0.07
    POSITIVE LOGITS
     improvements
    0.08
     aprim
    0.08
     förb
    0.08
     mejoras
    0.08
     Improvements
    0.08
     modernization
    0.08
     senare
    0.08
     later
    0.08
     verbessert
    0.08
    _optimizer
    0.08
    Act Density 0.099%

    No Known Activations