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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    still
    -0.07
     olive
    -0.07
    .xaml
    -0.07
    917
    -0.07
    711
    -0.07
    story
    -0.06
    371
    -0.06
     lounge
    -0.06
     moral
    -0.06
     DOJ
    -0.06
    POSITIVE LOGITS
    одатель
    0.07
    '):
    0.07
    原因
    0.06
    htdocs
    0.06
    ilecek
    0.06
    BD
    0.06
    봉
    0.06
    cular
    0.06
    ‌پ
    0.06
    %)↵
    0.06
    Act Density 0.042%

    No Known Activations