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

    Neuronpedia

    INDEX
    Explanations

    September

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.09
    =BitConverter
    -0.07
     by
    -0.07
     and
    -0.07
    ㄺ
    -0.07
     pizza
    -0.07
     hott
    -0.07
    赙
    -0.07
     a
    -0.07
    就好了
    -0.06
    POSITIVE LOGITS
    September
    0.07
     reasonable
    0.07
     Venezuela
    0.07
     commanding
    0.07
     foreground
    0.07
    ഗ
    0.07
    System
    0.07
    規定
    0.07
     услуги
    0.07
     Standing
    0.07
    Act Density 0.016%

    No Known Activations