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

    Neuronpedia

    INDEX
    Explanations

    substrate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ");↵↵↵
    -0.07
    保持
    -0.07
     corridor
    -0.07
     Announcement
    -0.07
    暴
    -0.07
     fingers
    -0.06
    dataSource
    -0.06
     фин
    -0.06
    нуться
    -0.06
    ้ช
    -0.06
    POSITIVE LOGITS
    icí
    0.06
    .cum
    0.06
    (std
    0.06
     mentor
    0.06
    .SE
    0.06
    .ImageIcon
    0.06
     Para
    0.06
    .Second
    0.05
     XPath
    0.05
    )...
    0.05
    Act Density 0.030%

    No Known Activations