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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical research literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “
    -0.06
     Barnes
    -0.06
     qr
    -0.06
    気に入
    -0.06
    eru
    -0.06
    站
    -0.06
    Cb
    -0.06
    /'
    -0.06
     fake
    -0.05
    -goal
    -0.05
    POSITIVE LOGITS
     SCREEN
    0.07
    ‌شود
    0.07
     रख
    0.07
    」↵
    0.07
     indem
    0.06
     *);↵↵
    0.06
    ัตร
    0.06
    ....↵↵
    0.06
    ือข
    0.06
     ROC
    0.06
    Act Density 0.005%

    No Known Activations