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

    Neuronpedia

    INDEX
    Explanations

    Mixed languages and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大全
    -0.08
     n't
    -0.08
     skor
    -0.08
     порядке
    -0.07
     muzie
    -0.07
     offert
    -0.07
     ਇੱਕ
    -0.07
     emf
    -0.07
    }:
    -0.07
    资讯
    -0.07
    POSITIVE LOGITS
     Hampton
    0.10
    ’hab
    0.08
     bisherigen
    0.08
     حسين
    0.08
     Buchanan
    0.08
     பத
    0.07
     �
    0.07
     хил
    0.07
     Murray
    0.07
     Rosen
    0.07
    Act Density 0.048%

    No Known Activations