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

    Neuronpedia

    INDEX
    Explanations

    python scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lydia
    -0.07
    欣
    -0.07
     پوش
    -0.07
    嘉
    -0.06
    heim
    -0.06
    mean
    -0.06
     Lottery
    -0.06
    uge
    -0.06
    .ToolStripSeparator
    -0.06
    urring
    -0.06
    POSITIVE LOGITS
    >-->↵
    0.07
    //↵↵↵
    0.07
    인지
    0.07
    (Expected
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
    .↵↵↵↵
    0.07
    _try
    0.07
    .debug
    0.06
    _logger
    0.06
    ].↵↵
    0.06
    Act Density 0.001%

    No Known Activations