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

    Neuronpedia

    INDEX
    Explanations

    Windsor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cait
    -0.08
    ABCDEFGHIJKLMNOP
    -0.07
    VectorXd
    -0.07
    (CancellationToken
    -0.06
    icens
    -0.06
    炎
    -0.06
    είς
    -0.06
     méd
    -0.06
    emek
    -0.06
     occupational
    -0.06
    POSITIVE LOGITS
     shutil
    0.07
    '↵↵↵
    0.07
    ↵↵↵
    0.06
     ґ
    0.06
     AVCapture
    0.06
    Ін
    0.06
    asic
    0.06
    ์↵
    0.06
    )↵↵↵
    0.06
    424
    0.06
    Act Density 0.016%

    No Known Activations