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

    Neuronpedia

    INDEX
    Explanations

    news/historical accounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rac
    -0.07
     öğrenc
    -0.06
    ジョ
    -0.06
    (zone
    -0.06
    arily
    -0.06
     pharmacy
    -0.06
    ジオ
    -0.06
    いう
    -0.06
    лок
    -0.06
    azole
    -0.06
    POSITIVE LOGITS
    )↵↵↵↵↵↵↵↵
    0.07
     precaution
    0.06
    .....
    0.06
     자
    0.06
     ارشد
    0.06
     آپ
    0.06
    .iloc
    0.06
    इसक
    0.06
     handwritten
    0.06
     tslint
    0.06
    Act Density 0.000%

    No Known Activations