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

    Neuronpedia

    INDEX
    Explanations

    Code, file paths, URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MGA
    -0.09
     caus
    -0.08
     BLUE
    -0.08
     maneuver
    -0.08
     Jee
    -0.08
     giro
    -0.08
     impeachment
    -0.07
     BAC
    -0.07
    [:,:,
    -0.07
    (:,:,
    -0.07
    POSITIVE LOGITS
    列表
    0.16
     목록
    0.14
     리스트
    0.13
     список
    0.13
     सूची
    0.13
    .txt
    0.13
     তাল
    0.13
     ಪಟ್ಟ
    0.13
     списка
    0.12
     seznam
    0.12
    Act Density 0.015%

    No Known Activations