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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.77
     <=",
    -0.73
    __":
    -0.72
     تضيفلها
    -0.69
    estacks
    -0.66
    }))
    -0.65
     समीक्षक
    -0.65
    Hauptartikel
    -0.65
    CloseOperation
    -0.64
     >=",
    -0.63
    POSITIVE LOGITS
    emin
    0.52
    ã
    0.50
    ENTE
    0.48
     mat
    0.48
    ses
    0.48
    än
    0.47
    ไร
    0.47
     Mat
    0.47
    racy
    0.47
    DbType
    0.47
    Act Density 0.012%

    No Known Activations